From ffc462465d27d768f001cc3fd89ee67dec30e493 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Tue, 6 Jan 2026 16:31:07 +0530 Subject: [PATCH] fix: remove display name --- ...odel_prices_and_context_window_backup.json | 6875 ++++------------- model_prices_and_context_window.json | 12 - 2 files changed, 1369 insertions(+), 5518 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c1b6787132..5baa9e1aa3 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4,7 +4,6 @@ "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", - "display_name": "human readable model name e.g. 'Llama 3.2 3B Instruct', 'GPT-4o', 'Grok 2', etc.", "file_search_cost_per_1k_calls": 0.0, "file_search_cost_per_gb_per_day": 0.0, "input_cost_per_audio_token": 0.0, @@ -14,8 +13,6 @@ "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, search", - "model_vendor": "used to group models by vendor e.g. openai, google, etc.", - "model_version": "used to group models by version e.g. v1, v2, etc.", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, "search_context_cost_per_query": { @@ -43,142 +40,104 @@ "vector_store_cost_per_gb_per_day": 0.0 }, "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { - "display_name": "Nova Canvas", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_image": 0.06 }, "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { - "display_name": "Stable Diffusion XL", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", - "model_vendor": "stability", - "model_version": "v1", "output_cost_per_image": 0.04 }, "1024-x-1024/dall-e-2": { - "display_name": "DALL-E 2", - "model_vendor": "openai", "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": { - "display_name": "Stable Diffusion XL", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", - "model_vendor": "stability", - "model_version": "v1", "output_cost_per_image": 0.08 }, "256-x-256/dall-e-2": { - "display_name": "DALL-E 2", - "model_vendor": "openai", "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": { - "display_name": "Stable Diffusion XL", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", - "model_vendor": "stability", - "model_version": "v0", "output_cost_per_image": 0.018 }, "512-x-512/dall-e-2": { - "display_name": "DALL-E 2", - "model_vendor": "openai", "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": { - "display_name": "Stable Diffusion XL", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", - "model_vendor": "stability", - "model_version": "v0", "output_cost_per_image": 0.036 }, "ai21.j2-mid-v1": { - "display_name": "Jurassic-2 Mid", "input_cost_per_token": 1.25e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "ai21", - "model_version": "v1", "output_cost_per_token": 1.25e-05 }, "ai21.j2-ultra-v1": { - "display_name": "Jurassic-2 Ultra", "input_cost_per_token": 1.88e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "ai21", - "model_version": "v1", "output_cost_per_token": 1.88e-05 }, "ai21.jamba-1-5-large-v1:0": { - "display_name": "Jamba 1.5 Large", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "model_vendor": "ai21", - "model_version": "1.5-large-v1:0", "output_cost_per_token": 8e-06 }, "ai21.jamba-1-5-mini-v1:0": { - "display_name": "Jamba 1.5 Mini", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "model_vendor": "ai21", - "model_version": "1.5-mini-v1:0", "output_cost_per_token": 4e-07 }, "ai21.jamba-instruct-v1:0": { - "display_name": "Jamba Instruct", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "ai21", - "model_version": "instruct-v1:0", "output_cost_per_token": 7e-07, "supports_system_messages": true }, "aiml/dall-e-2": { - "display_name": "DALL-E 2", - "model_vendor": "openai", "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" @@ -191,8 +150,6 @@ ] }, "aiml/dall-e-3": { - "display_name": "DALL-E 3", - "model_vendor": "openai", "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" @@ -205,13 +162,11 @@ ] }, "aiml/flux-pro": { - "display_name": "FLUX Pro", "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.053, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ @@ -219,35 +174,27 @@ ] }, "aiml/flux-pro/v1.1": { - "display_name": "FLUX Pro", "litellm_provider": "aiml", "mode": "image_generation", - "model_vendor": "black-forest-labs", - "model_version": "v1.1", "output_cost_per_image": 0.042, "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-pro/v1.1-ultra": { - "display_name": "FLUX Pro Ultra", "litellm_provider": "aiml", "mode": "image_generation", - "model_vendor": "black-forest-labs", - "model_version": "v1.1-ultra", "output_cost_per_image": 0.063, "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-realism": { - "display_name": "FLUX Realism", "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro - Professional-grade image generation model" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.037, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ @@ -255,13 +202,11 @@ ] }, "aiml/flux/dev": { - "display_name": "FLUX Dev", "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.026, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ @@ -269,13 +214,11 @@ ] }, "aiml/flux/kontext-max/text-to-image": { - "display_name": "FLUX Kontext Max", "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.084, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ @@ -283,13 +226,11 @@ ] }, "aiml/flux/kontext-pro/text-to-image": { - "display_name": "FLUX Kontext Pro", "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.042, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ @@ -297,32 +238,48 @@ ] }, "aiml/flux/schnell": { - "display_name": "FLUX Schnell", "litellm_provider": "aiml", "metadata": { "notes": "Flux Schnell - Fast generation model optimized for speed" }, "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.003, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, + "aiml/google/imagen-4.0-ultra-generate-001": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" + }, + "mode": "image_generation", + "output_cost_per_image": 0.063, + "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/google/nano-banana-pro": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" + }, + "mode": "image_generation", + "output_cost_per_image": 0.1575, + "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "amazon.nova-canvas-v1:0": { - "display_name": "Nova Canvas", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_image": 0.06 }, "us.writer.palmyra-x4-v1:0": { - "display_name": "Writer.palmyra X4 V1:0", - "model_vendor": "google", - "model_version": "0", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -334,9 +291,6 @@ "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { - "display_name": "Writer.palmyra X5 V1:0", - "model_vendor": "google", - "model_version": "0", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, @@ -348,9 +302,6 @@ "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { - "display_name": "Palmyra X4 V1:0", - "model_vendor": "google", - "model_version": "0", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -362,9 +313,6 @@ "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { - "display_name": "Palmyra X5 V1:0", - "model_vendor": "google", - "model_version": "0", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, @@ -376,15 +324,12 @@ "supports_pdf_input": true }, "amazon.nova-lite-v1:0": { - "display_name": "Nova Lite", "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, "supports_pdf_input": true, @@ -393,8 +338,6 @@ "supports_vision": true }, "amazon.nova-2-lite-v1:0": { - "display_name": "Nova 2 Lite", - "model_vendor": "amazon", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "bedrock_converse", @@ -412,8 +355,6 @@ "supports_vision": true }, "apac.amazon.nova-2-lite-v1:0": { - "display_name": "Nova 2 Lite", - "model_vendor": "amazon", "cache_read_input_token_cost": 8.25e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock_converse", @@ -431,8 +372,6 @@ "supports_vision": true }, "eu.amazon.nova-2-lite-v1:0": { - "display_name": "Nova 2 Lite", - "model_vendor": "amazon", "cache_read_input_token_cost": 8.25e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock_converse", @@ -450,8 +389,6 @@ "supports_vision": true }, "us.amazon.nova-2-lite-v1:0": { - "display_name": "Nova 2 Lite", - "model_vendor": "amazon", "cache_read_input_token_cost": 8.25e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock_converse", @@ -468,31 +405,26 @@ "supports_video_input": true, "supports_vision": true }, + "amazon.nova-micro-v1:0": { - "display_name": "Nova Micro", "input_cost_per_token": 3.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true }, "amazon.nova-pro-v1:0": { - "display_name": "Nova Pro", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -501,7 +433,6 @@ "supports_vision": true }, "amazon.rerank-v1:0": { - "display_name": "Amazon Rerank", "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", @@ -512,12 +443,9 @@ "max_tokens": 32000, "max_tokens_per_document_chunk": 512, "mode": "rerank", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 0.0 }, "amazon.titan-embed-image-v1": { - "display_name": "Titan Embed Image", "input_cost_per_image": 6e-05, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", @@ -527,8 +455,6 @@ "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "mode": "embedding", - "model_vendor": "amazon", - "model_version": "v1", "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", @@ -536,57 +462,42 @@ "supports_image_input": true }, "amazon.titan-embed-text-v1": { - "display_name": "Titan Embed Text", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", - "model_version": "v1", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "amazon.titan-embed-text-v2:0": { - "display_name": "Titan Embed Text", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", - "model_version": "v2:0", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "amazon.titan-image-generator-v1": { - "display_name": "Titan Image Generator", "input_cost_per_image": 0.0, - "litellm_provider": "bedrock", - "mode": "image_generation", - "model_vendor": "amazon", - "model_version": "v1", "output_cost_per_image": 0.008, + "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_512_and_512_pixels": 0.01, "output_cost_per_image_above_512_and_512_pixels_and_premium_image": 0.012, - "output_cost_per_image_premium_image": 0.01 + "litellm_provider": "bedrock", + "mode": "image_generation" }, "amazon.titan-image-generator-v2": { - "display_name": "Titan Image Generator", "input_cost_per_image": 0.0, - "litellm_provider": "bedrock", - "mode": "image_generation", - "model_vendor": "amazon", - "model_version": "v2", "output_cost_per_image": 0.008, + "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_1024_and_1024_pixels": 0.01, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012, - "output_cost_per_image_premium_image": 0.01 + "litellm_provider": "bedrock", + "mode": "image_generation" }, "amazon.titan-image-generator-v2:0": { - "display_name": "Titan Image Generator V2:0", - "model_vendor": "amazon", - "model_version": "0", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, @@ -596,131 +507,101 @@ "mode": "image_generation" }, "twelvelabs.marengo-embed-2-7-v1:0": { - "display_name": "Marengo Embed", "input_cost_per_token": 7e-05, "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "embedding", - "model_vendor": "twelve-labs", - "model_version": "2.7-v1:0", "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": { - "display_name": "Marengo Embed", - "input_cost_per_audio_per_second": 0.00014, - "input_cost_per_image": 0.0001, "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", - "model_vendor": "twelve-labs", - "model_version": "2.7-v1:0", "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": { - "display_name": "Marengo Embed", - "input_cost_per_audio_per_second": 0.00014, - "input_cost_per_image": 0.0001, "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", - "model_vendor": "twelve-labs", - "model_version": "2.7-v1:0", "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": { - "display_name": "Pegasus", "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", - "model_vendor": "twelve-labs", - "model_version": "1.2-v1:0", - "output_cost_per_token": 7.5e-06, "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { - "display_name": "Pegasus", "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", - "model_vendor": "twelve-labs", - "model_version": "1.2-v1:0", - "output_cost_per_token": 7.5e-06, "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { - "display_name": "Pegasus", "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", - "model_vendor": "twelve-labs", - "model_version": "1.2-v1:0", - "output_cost_per_token": 7.5e-06, "supports_video_input": true }, "amazon.titan-text-express-v1": { - "display_name": "Titan Text Express", "input_cost_per_token": 1.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1", "output_cost_per_token": 1.7e-06 }, "amazon.titan-text-lite-v1": { - "display_name": "Titan Text Lite", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1", "output_cost_per_token": 4e-07 }, "amazon.titan-text-premier-v1:0": { - "display_name": "Titan Text Premier", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "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, - "display_name": "Claude 3.5 Haiku", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022-v1:0", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -732,15 +613,12 @@ "anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, - "display_name": "Claude 4.5 Haiku", "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251001-v1:0", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, @@ -757,15 +635,12 @@ "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, - "display_name": "Claude 4.5 Haiku", "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251001", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, @@ -780,15 +655,12 @@ "tool_use_system_prompt_tokens": 346 }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude 3.5 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -799,15 +671,12 @@ "anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "display_name": "Claude 3.5 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022-v2:0", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -821,15 +690,12 @@ "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_read_input_token_cost": 3.6e-07, - "display_name": "Claude 3.7 Sonnet", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -844,15 +710,12 @@ "anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "display_name": "Claude 3.7 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250219-v1:0", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -865,15 +728,12 @@ "supports_vision": true }, "anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude 3 Haiku", "input_cost_per_token": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240307-v1:0", "output_cost_per_token": 1.25e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -882,15 +742,12 @@ "supports_vision": true }, "anthropic.claude-3-opus-20240229-v1:0": { - "display_name": "Claude 3 Opus", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240229-v1:0", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_response_schema": true, @@ -898,15 +755,12 @@ "supports_vision": true }, "anthropic.claude-3-sonnet-20240229-v1:0": { - "display_name": "Claude 3 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240229-v1:0", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -915,30 +769,24 @@ "supports_vision": true }, "anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v1", "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, - "display_name": "Claude 4.1 Opus", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250805-v1:0", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -959,15 +807,12 @@ "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, - "display_name": "Claude 4 Opus", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250514-v1:0", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -988,15 +833,12 @@ "anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, - "display_name": "Claude 4.5 Opus", "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251101-v1:0", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -1016,21 +858,18 @@ }, "anthropic.claude-sonnet-4-20250514-v1:0": { "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, - "display_name": "Claude 4 Sonnet", "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", - "model_vendor": "anthropic", - "model_version": "20250514-v1:0", "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, @@ -1049,21 +888,18 @@ }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "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, - "display_name": "Claude 4.5 Sonnet", "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": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250929-v1:0", "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, @@ -1081,185 +917,149 @@ "tool_use_system_prompt_tokens": 159 }, "anthropic.claude-v1": { - "display_name": "Claude", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v1", "output_cost_per_token": 2.4e-05 }, "anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v2:1", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { - "display_name": "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", - "model_vendor": "huggingface", "output_cost_per_token": 1.5e-07 }, "anyscale/codellama/CodeLlama-34b-Instruct-hf": { - "display_name": "CodeLlama 34B Instruct", "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 1e-06 }, "anyscale/codellama/CodeLlama-70b-Instruct-hf": { - "display_name": "CodeLlama 70B Instruct", "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "meta", "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": { - "display_name": "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", - "model_vendor": "google", "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": { - "display_name": "Llama 2 13B Chat", "input_cost_per_token": 2.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 2.5e-07 }, "anyscale/meta-llama/Llama-2-70b-chat-hf": { - "display_name": "Llama 2 70B Chat", "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 1e-06 }, "anyscale/meta-llama/Llama-2-7b-chat-hf": { - "display_name": "Llama 2 7B Chat", "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 1.5e-07 }, "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { - "display_name": "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", - "model_vendor": "meta", "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": { - "display_name": "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", - "model_vendor": "meta", "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": { - "display_name": "Mistral 7B Instruct", "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0.1", "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": { - "display_name": "Mixtral 8x22B Instruct", "input_cost_per_token": 9e-07, "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0.1", "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": { - "display_name": "Mixtral 8x7B Instruct", "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0.1", "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": { - "display_name": "Nova Lite", "input_cost_per_token": 6.3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, "supports_pdf_input": true, @@ -1268,30 +1068,24 @@ "supports_vision": true }, "apac.amazon.nova-micro-v1:0": { - "display_name": "Nova Micro", "input_cost_per_token": 3.7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "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": { - "display_name": "Nova Pro", "input_cost_per_token": 8.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 3.36e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -1300,15 +1094,12 @@ "supports_vision": true }, "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude 3.5 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -1319,15 +1110,12 @@ "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "display_name": "Claude 3.5 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022-v2:0", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -1339,15 +1127,12 @@ "supports_vision": true }, "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude 3 Haiku", "input_cost_per_token": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240307-v1:0", "output_cost_per_token": 1.25e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -1358,15 +1143,12 @@ "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, - "display_name": "Claude 4.5 Haiku", "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251001-v1:0", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, @@ -1381,15 +1163,12 @@ "tool_use_system_prompt_tokens": 346 }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "display_name": "Claude 3 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240229-v1:0", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -1399,21 +1178,18 @@ }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "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, - "display_name": "Claude 4 Sonnet", "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", - "model_vendor": "anthropic", - "model_version": "20250514-v1:0", "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, @@ -1431,38 +1207,31 @@ "tool_use_system_prompt_tokens": 159 }, "assemblyai/best": { - "display_name": "AssemblyAI Best", "input_cost_per_second": 3.333e-05, "litellm_provider": "assemblyai", "mode": "audio_transcription", - "model_vendor": "assemblyai", "output_cost_per_second": 0.0 }, "assemblyai/nano": { - "display_name": "AssemblyAI Nano", "input_cost_per_second": 0.00010278, "litellm_provider": "assemblyai", "mode": "audio_transcription", - "model_vendor": "assemblyai", "output_cost_per_second": 0.0 }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, - "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_read_input_token_cost": 3.3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, - "display_name": "Claude 4.5 Sonnet", "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250929-v1:0", "output_cost_per_token": 1.65e-05, - "output_cost_per_token_above_200k_tokens": 2.475e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1480,25 +1249,21 @@ "tool_use_system_prompt_tokens": 346 }, "azure/ada": { - "display_name": "Ada", "input_cost_per_token": 1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "model_vendor": "openai", "output_cost_per_token": 0.0 }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, - "display_name": "Codex Mini", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 6e-06, "supported_endpoints": [ "/v1/responses" @@ -1521,26 +1286,22 @@ "supports_vision": true }, "azure/command-r-plus": { - "display_name": "Command R+", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "cohere", "output_cost_per_token": 1.5e-05, "supports_function_calling": true }, "azure_ai/claude-haiku-4-5": { - "display_name": "Claude 4.5 Haiku", "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -1553,14 +1314,12 @@ "supports_vision": true }, "azure_ai/claude-opus-4-1": { - "display_name": "Claude 4.1 Opus", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -1573,14 +1332,12 @@ "supports_vision": true }, "azure_ai/claude-sonnet-4-5": { - "display_name": "Claude 4.5 Sonnet", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -1593,14 +1350,12 @@ "supports_vision": true }, "azure/computer-use-preview": { - "display_name": "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", - "model_vendor": "openai", "output_cost_per_token": 1.2e-05, "supported_endpoints": [ "/v1/responses" @@ -1623,23 +1378,32 @@ }, "azure/container": { "code_interpreter_cost_per_session": 0.03, - "display_name": "Container", "litellm_provider": "azure", + "mode": "chat" + }, + "azure_ai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "model_vendor": "openai" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, "azure/eu/gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 1.375e-06, "deprecation_date": "2026-02-27", - "display_name": "GPT-4o", + "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", - "model_vendor": "openai", - "model_version": "2024-08-06", "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -1649,17 +1413,14 @@ "supports_vision": true }, "azure/eu/gpt-4o-2024-11-20": { - "cache_creation_input_token_cost": 1.38e-06, "deprecation_date": "2026-03-01", - "display_name": "GPT-4o", + "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", - "model_vendor": "openai", - "model_version": "2024-11-20", "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -1669,15 +1430,12 @@ }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, - "display_name": "GPT-4o Mini", "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-07-18", "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -1689,7 +1447,6 @@ "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, - "display_name": "GPT-4o Mini Realtime", "input_cost_per_audio_token": 1.1e-05, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure", @@ -1697,8 +1454,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-2024-12-17", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, "supports_audio_input": true, @@ -1711,7 +1466,6 @@ "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, - "display_name": "GPT-4o Realtime", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -1719,8 +1473,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-2024-10-01", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, "supports_audio_input": true, @@ -1733,7 +1485,6 @@ "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, - "display_name": "GPT-4o Realtime", "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -1741,8 +1492,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-2024-12-17", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2.2e-05, "supported_modalities": [ @@ -1762,15 +1511,12 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, - "display_name": "GPT-5", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -1797,15 +1543,12 @@ }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, - "display_name": "GPT-5 Mini", "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 2.2e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -1832,14 +1575,12 @@ }, "azure/eu/gpt-5.1": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -1867,14 +1608,12 @@ }, "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1 Chat", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -1902,14 +1641,12 @@ }, "azure/eu/gpt-5.1-codex": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1 Codex", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/responses" @@ -1934,14 +1671,12 @@ }, "azure/eu/gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.8e-08, - "display_name": "GPT-5.1 Codex Mini", "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 2.2e-06, "supported_endpoints": [ "/v1/responses" @@ -1966,15 +1701,12 @@ }, "azure/eu/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, - "display_name": "GPT-5 Nano", "input_cost_per_token": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 4.4e-07, "supported_endpoints": [ "/v1/chat/completions", @@ -2001,15 +1733,12 @@ }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "display_name": "o1", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-12-17", "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2019,7 +1748,6 @@ }, "azure/eu/o1-mini-2024-09-12": { "cache_read_input_token_cost": 6.05e-07, - "display_name": "o1 Mini", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -2027,8 +1755,6 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-09-12", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "supports_function_calling": true, @@ -2038,15 +1764,12 @@ }, "azure/eu/o1-preview-2024-09-12": { "cache_read_input_token_cost": 8.25e-06, - "display_name": "o1 Preview", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "preview-2024-09-12", "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2055,7 +1778,6 @@ }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "display_name": "o3 Mini", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -2063,8 +1785,6 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-01-31", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "supports_prompt_caching": true, @@ -2075,15 +1795,12 @@ "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-02-27", - "display_name": "GPT-4o", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-08-06", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2095,15 +1812,12 @@ "azure/global-standard/gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-03-01", - "display_name": "GPT-4o", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-11-20", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2112,14 +1826,12 @@ "supports_vision": true }, "azure/global-standard/gpt-4o-mini": { - "display_name": "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", - "model_vendor": "openai", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2128,17 +1840,14 @@ "supports_vision": true }, "azure/global/gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-02-27", - "display_name": "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", - "model_vendor": "openai", - "model_version": "2024-08-06", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2148,17 +1857,14 @@ "supports_vision": true }, "azure/global/gpt-4o-2024-11-20": { - "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-03-01", - "display_name": "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", - "model_vendor": "openai", - "model_version": "2024-11-20", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2169,14 +1875,12 @@ }, "azure/global/gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -2204,14 +1908,12 @@ }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1 Chat", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -2239,14 +1941,12 @@ }, "azure/global/gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1 Codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/responses" @@ -2271,14 +1971,12 @@ }, "azure/global/gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-5.1 Codex Mini", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 2e-06, "supported_endpoints": [ "/v1/responses" @@ -2302,69 +2000,56 @@ "supports_vision": true }, "azure/gpt-3.5-turbo": { - "display_name": "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", - "model_vendor": "openai", "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", - "display_name": "GPT-3.5 Turbo", "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "0125", "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": { - "display_name": "GPT-3.5 Turbo Instruct", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "model_vendor": "openai", - "model_version": "instruct-0914", "output_cost_per_token": 2e-06 }, "azure/gpt-35-turbo": { - "display_name": "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", - "model_vendor": "openai", "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", - "display_name": "GPT-3.5 Turbo", "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "0125", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2372,15 +2057,12 @@ }, "azure/gpt-35-turbo-0301": { "deprecation_date": "2025-02-13", - "display_name": "GPT-3.5 Turbo", "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4097, "mode": "chat", - "model_vendor": "openai", - "model_version": "0301", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2388,15 +2070,12 @@ }, "azure/gpt-35-turbo-0613": { "deprecation_date": "2025-02-13", - "display_name": "GPT-3.5 Turbo", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4097, "mode": "chat", - "model_vendor": "openai", - "model_version": "0613", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2404,173 +2083,139 @@ }, "azure/gpt-35-turbo-1106": { "deprecation_date": "2025-03-31", - "display_name": "GPT-3.5 Turbo", "input_cost_per_token": 1e-06, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "1106", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-35-turbo-16k": { - "display_name": "GPT-3.5 Turbo 16K", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4e-06, "supports_tool_choice": true }, "azure/gpt-35-turbo-16k-0613": { - "display_name": "GPT-3.5 Turbo 16K", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "16k-0613", "output_cost_per_token": 4e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-35-turbo-instruct": { - "display_name": "GPT-3.5 Turbo Instruct", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "model_vendor": "openai", "output_cost_per_token": 2e-06 }, "azure/gpt-35-turbo-instruct-0914": { - "display_name": "GPT-3.5 Turbo Instruct", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "model_vendor": "openai", - "model_version": "instruct-0914", "output_cost_per_token": 2e-06 }, "azure/gpt-4": { - "display_name": "GPT-4", "input_cost_per_token": 3e-05, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0125-preview": { - "display_name": "GPT-4 Turbo Preview", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "0125-preview", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0613": { - "display_name": "GPT-4", "input_cost_per_token": 3e-05, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "0613", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-1106-preview": { - "display_name": "GPT-4 Turbo Preview", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "1106-preview", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-32k": { - "display_name": "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", - "model_vendor": "openai", "output_cost_per_token": 0.00012, "supports_tool_choice": true }, "azure/gpt-4-32k-0613": { - "display_name": "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", - "model_vendor": "openai", - "model_version": "32k-0613", "output_cost_per_token": 0.00012, "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "display_name": "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", - "model_vendor": "openai", "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": { - "display_name": "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", - "model_vendor": "openai", - "model_version": "2024-04-09", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2578,22 +2223,18 @@ "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { - "display_name": "GPT-4 Turbo Vision", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "vision-preview", "output_cost_per_token": 3e-05, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4.1": { "cache_read_input_token_cost": 5e-07, - "display_name": "GPT-4.1", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", @@ -2601,7 +2242,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "supported_endpoints": [ @@ -2627,9 +2267,8 @@ "supports_web_search": false }, "azure/gpt-4.1-2025-04-14": { - "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-11-04", - "display_name": "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", @@ -2637,8 +2276,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-14", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "supported_endpoints": [ @@ -2665,7 +2302,6 @@ }, "azure/gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, - "display_name": "GPT-4.1 Mini", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "azure", @@ -2673,7 +2309,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "supported_endpoints": [ @@ -2699,9 +2334,8 @@ "supports_web_search": false }, "azure/gpt-4.1-mini-2025-04-14": { - "cache_read_input_token_cost": 1e-07, "deprecation_date": "2026-11-04", - "display_name": "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", @@ -2709,8 +2343,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "mini-2025-04-14", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "supported_endpoints": [ @@ -2737,7 +2369,6 @@ }, "azure/gpt-4.1-nano": { "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-4.1 Nano", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", @@ -2745,7 +2376,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "supported_endpoints": [ @@ -2770,9 +2400,8 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-11-04", - "display_name": "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", @@ -2780,8 +2409,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "nano-2025-04-14", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "supported_endpoints": [ @@ -2807,7 +2434,6 @@ }, "azure/gpt-4.5-preview": { "cache_read_input_token_cost": 3.75e-05, - "display_name": "GPT-4.5 Preview", "input_cost_per_token": 7.5e-05, "input_cost_per_token_batches": 3.75e-05, "litellm_provider": "azure", @@ -2815,7 +2441,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 7.5e-05, "supports_function_calling": true, @@ -2828,14 +2453,12 @@ }, "azure/gpt-4o": { "cache_read_input_token_cost": 1.25e-06, - "display_name": "GPT-4o", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2845,15 +2468,12 @@ "supports_vision": true }, "azure/gpt-4o-2024-05-13": { - "display_name": "GPT-4o", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-05-13", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2862,17 +2482,14 @@ "supports_vision": true }, "azure/gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-02-27", - "display_name": "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", - "model_vendor": "openai", - "model_version": "2024-08-06", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2882,17 +2499,14 @@ "supports_vision": true }, "azure/gpt-4o-2024-11-20": { - "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-03-01", - "display_name": "GPT-4o", + "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", - "model_vendor": "openai", - "model_version": "2024-11-20", "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -2902,7 +2516,6 @@ "supports_vision": true }, "azure/gpt-audio-2025-08-28": { - "display_name": "GPT Audio", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -2910,8 +2523,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-28", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -2936,7 +2547,6 @@ "supports_vision": false }, "azure/gpt-audio-mini-2025-10-06": { - "display_name": "GPT Audio Mini", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", @@ -2944,8 +2554,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "mini-2025-10-06", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ @@ -2970,7 +2578,6 @@ "supports_vision": false }, "azure/gpt-4o-audio-preview-2024-12-17": { - "display_name": "GPT-4o Audio Preview", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -2978,8 +2585,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "audio-preview-2024-12-17", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -3005,14 +2610,12 @@ }, "azure/gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, - "display_name": "GPT-4o Mini", "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -3023,15 +2626,12 @@ }, "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, - "display_name": "GPT-4o Mini", "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-07-18", "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -3041,7 +2641,6 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "display_name": "GPT-4o Mini Audio Preview", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -3049,8 +2648,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "audio-preview-2024-12-17", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -3077,7 +2674,6 @@ "azure/gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, - "display_name": "GPT-4o Mini Realtime Preview", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", @@ -3085,8 +2681,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-preview-2024-12-17", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supports_audio_input": true, @@ -3099,7 +2693,6 @@ "azure/gpt-realtime-2025-08-28": { "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_token_cost": 4e-06, - "display_name": "GPT Realtime", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image": 5e-06, "input_cost_per_token": 4e-06, @@ -3108,8 +2701,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-28", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "supported_endpoints": [ @@ -3134,7 +2725,6 @@ "azure/gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, - "display_name": "GPT Realtime Mini", "input_cost_per_audio_token": 1e-05, "input_cost_per_image": 8e-07, "input_cost_per_token": 6e-07, @@ -3143,8 +2733,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "mini-2025-10-06", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ @@ -3167,25 +2755,21 @@ "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { - "display_name": "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", - "model_vendor": "openai", "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-mini-tts": { - "display_name": "GPT-4o Mini TTS", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "mode": "audio_speech", - "model_vendor": "openai", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, @@ -3203,7 +2787,6 @@ "azure/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2e-05, "cache_read_input_token_cost": 2.5e-06, - "display_name": "GPT-4o Realtime Preview", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -3211,8 +2794,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-preview-2024-10-01", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, "supports_audio_input": true, @@ -3224,7 +2805,6 @@ }, "azure/gpt-4o-realtime-preview-2024-12-17": { "cache_read_input_token_cost": 2.5e-06, - "display_name": "GPT-4o Realtime Preview", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -3232,8 +2812,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "realtime-preview-2024-12-17", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, "supported_modalities": [ @@ -3252,37 +2830,32 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "display_name": "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", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { - "display_name": "GPT-4o Transcribe Diarize", "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", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" ] }, - "azure/gpt-5.1-2025-11-13": { + "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, - "display_name": "GPT-5.1", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", @@ -3290,8 +2863,6 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-11-13", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, "supported_endpoints": [ @@ -3313,15 +2884,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_service_tier": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "azure/gpt-5.1-chat-2025-11-13": { + "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, - "display_name": "GPT-5.1 Chat", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", @@ -3329,8 +2899,6 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "chat-2025-11-13", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, "supported_endpoints": [ @@ -3356,10 +2924,9 @@ "supports_tool_choice": false, "supports_vision": true }, - "azure/gpt-5.1-codex-2025-11-13": { + "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, - "display_name": "GPT-5.1 Codex", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", @@ -3367,8 +2934,6 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", - "model_version": "codex-2025-11-13", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, "supported_endpoints": [ @@ -3395,7 +2960,6 @@ "azure/gpt-5.1-codex-mini-2025-11-13": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, - "display_name": "GPT-5.1 Codex Mini", "input_cost_per_token": 2.5e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", @@ -3403,8 +2967,6 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", - "model_version": "codex-mini-2025-11-13", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, "supported_endpoints": [ @@ -3430,14 +2992,12 @@ }, "azure/gpt-5": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -3464,15 +3024,12 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -3499,14 +3056,12 @@ }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5 Chat", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "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": [ @@ -3534,14 +3089,12 @@ }, "azure/gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5 Chat", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -3568,14 +3121,12 @@ }, "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5 Codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/responses" @@ -3600,14 +3151,12 @@ }, "azure/gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-5 Mini", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 2e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -3634,15 +3183,12 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-5 Mini", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 2e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -3669,14 +3215,12 @@ }, "azure/gpt-5-nano": { "cache_read_input_token_cost": 5e-09, - "display_name": "GPT-5 Nano", "input_cost_per_token": 5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4e-07, "supported_endpoints": [ "/v1/chat/completions", @@ -3703,15 +3247,12 @@ }, "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, - "display_name": "GPT-5 Nano", "input_cost_per_token": 5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 4e-07, "supported_endpoints": [ "/v1/chat/completions", @@ -3737,14 +3278,12 @@ "supports_vision": true }, "azure/gpt-5-pro": { - "display_name": "GPT-5 Pro", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 400000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "supported_endpoints": [ @@ -3769,14 +3308,12 @@ }, "azure/gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -3804,14 +3341,12 @@ }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1 Chat", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -3839,14 +3374,12 @@ }, "azure/gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, - "display_name": "GPT-5.1 Codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/responses" @@ -3870,9 +3403,6 @@ "supports_vision": true }, "azure/gpt-5.1-codex-max": { - "display_name": "GPT 5.1 Codex Max", - "model_vendor": "openai", - "model_version": "5.1", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", @@ -3904,14 +3434,12 @@ }, "azure/gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-5.1 Codex Mini", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 2e-06, "supported_endpoints": [ "/v1/responses" @@ -3935,9 +3463,6 @@ "supports_vision": true }, "azure/gpt-5.2": { - "display_name": "GPT 5.2", - "model_vendor": "openai", - "model_version": "5.2", "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", @@ -3971,9 +3496,6 @@ "supports_vision": true }, "azure/gpt-5.2-2025-12-11": { - "display_name": "GPT 5.2 2025 12 11", - "model_vendor": "openai", - "model_version": "2025-12-11", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, @@ -4010,10 +3532,41 @@ "supports_service_tier": true, "supports_vision": true }, + "azure/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/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-5.2-chat-2025-12-11": { - "display_name": "GPT 5.2 Chat 2025 12 11", - "model_vendor": "openai", - "model_version": "2025-12-11", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, @@ -4048,16 +3601,13 @@ "supports_vision": true }, "azure/gpt-5.2-pro": { - "display_name": "GPT 5.2 Pro", - "model_vendor": "openai", - "model_version": "5.2", "input_cost_per_token": 2.1e-05, "litellm_provider": "azure", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 1.68e-04, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -4082,16 +3632,13 @@ "supports_web_search": true }, "azure/gpt-5.2-pro-2025-12-11": { - "display_name": "GPT 5.2 Pro 2025 12 11", - "model_vendor": "openai", - "model_version": "2025-12-11", "input_cost_per_token": 2.1e-05, "litellm_provider": "azure", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 1.68e-04, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -4116,43 +3663,37 @@ "supports_web_search": true }, "azure/gpt-image-1": { - "display_name": "GPT Image 1", - "model_vendor": "openai", - "input_cost_per_pixel": 4.0054321e-08, + "cache_read_input_image_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_image_token": 1e-05, + "input_cost_per_token": 5e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "output_cost_per_image_token": 4e-05, "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "display_name": "DALL-E 3 HD", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 HD", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 HD", - "model_vendor": "openai", "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": { - "display_name": "GPT Image 1 High", - "model_vendor": "openai", "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -4162,8 +3703,6 @@ ] }, "azure/high/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 High", - "model_vendor": "openai", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -4173,8 +3712,6 @@ ] }, "azure/high/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 High", - "model_vendor": "openai", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -4184,8 +3721,6 @@ ] }, "azure/low/1024-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Low", - "model_vendor": "openai", "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4195,8 +3730,6 @@ ] }, "azure/low/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 Low", - "model_vendor": "openai", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4206,8 +3739,6 @@ ] }, "azure/low/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Low", - "model_vendor": "openai", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4217,8 +3748,6 @@ ] }, "azure/medium/1024-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Medium", - "model_vendor": "openai", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4228,8 +3757,6 @@ ] }, "azure/medium/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 Medium", - "model_vendor": "openai", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4239,8 +3766,6 @@ ] }, "azure/medium/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Medium", - "model_vendor": "openai", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4250,19 +3775,45 @@ ] }, "azure/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini", - "model_vendor": "openai", - "input_cost_per_pixel": 8.0566406e-09, + "cache_read_input_image_token_cost": 2.5e-07, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_image_token": 2.5e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "output_cost_per_image_token": 8e-06, "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3.2e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3.2e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" ] }, "azure/low/1024-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low", - "model_vendor": "openai", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4272,8 +3823,6 @@ ] }, "azure/low/1024-x-1536/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low", - "model_vendor": "openai", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4283,8 +3832,6 @@ ] }, "azure/low/1536-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low", - "model_vendor": "openai", "input_cost_per_pixel": 2.0345052083e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4294,8 +3841,6 @@ ] }, "azure/medium/1024-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium", - "model_vendor": "openai", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4305,8 +3850,6 @@ ] }, "azure/medium/1024-x-1536/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium", - "model_vendor": "openai", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4316,8 +3859,6 @@ ] }, "azure/medium/1536-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium", - "model_vendor": "openai", "input_cost_per_pixel": 7.9752604167e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -4327,8 +3868,6 @@ ] }, "azure/high/1024-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini High", - "model_vendor": "openai", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4338,8 +3877,6 @@ ] }, "azure/high/1024-x-1536/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini High", - "model_vendor": "openai", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4349,8 +3886,6 @@ ] }, "azure/high/1536-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini High", - "model_vendor": "openai", "input_cost_per_pixel": 3.1575520833e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -4360,38 +3895,31 @@ ] }, "azure/mistral-large-2402": { - "display_name": "Mistral Large", "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2402", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/mistral-large-latest": { - "display_name": "Mistral Large", "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "mistral", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/o1": { "cache_read_input_token_cost": 7.5e-06, - "display_name": "o1", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4402,15 +3930,12 @@ }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, - "display_name": "o1", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-12-17", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4421,14 +3946,12 @@ }, "azure/o1-mini": { "cache_read_input_token_cost": 6.05e-07, - "display_name": "o1 Mini", "input_cost_per_token": 1.21e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4.84e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4438,15 +3961,12 @@ }, "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, - "display_name": "o1 Mini", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-09-12", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4456,14 +3976,12 @@ }, "azure/o1-preview": { "cache_read_input_token_cost": 7.5e-06, - "display_name": "o1 Preview", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4473,15 +3991,12 @@ }, "azure/o1-preview-2024-09-12": { "cache_read_input_token_cost": 7.5e-06, - "display_name": "o1 Preview", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-09-12", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4492,14 +4007,12 @@ }, "azure/o3": { "cache_read_input_token_cost": 5e-07, - "display_name": "o3", "input_cost_per_token": 2e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 8e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -4524,15 +4037,12 @@ "azure/o3-2025-04-16": { "deprecation_date": "2026-04-16", "cache_read_input_token_cost": 5e-07, - "display_name": "o3", "input_cost_per_token": 2e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-16", "output_cost_per_token": 8e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -4556,14 +4066,12 @@ }, "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, - "display_name": "o3 Deep Research", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 4e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -4590,14 +4098,12 @@ }, "azure/o3-mini": { "cache_read_input_token_cost": 5.5e-07, - "display_name": "o3 Mini", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4.4e-06, "supports_prompt_caching": true, "supports_reasoning": true, @@ -4607,15 +4113,12 @@ }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, - "display_name": "o3 Mini", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-01-31", "output_cost_per_token": 4.4e-06, "supports_prompt_caching": true, "supports_reasoning": true, @@ -4623,7 +4126,6 @@ "supports_vision": false }, "azure/o3-pro": { - "display_name": "o3 Pro", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -4631,7 +4133,6 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, "supported_endpoints": [ @@ -4655,7 +4156,6 @@ "supports_vision": true }, "azure/o3-pro-2025-06-10": { - "display_name": "o3 Pro", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -4663,8 +4163,6 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", - "model_vendor": "openai", - "model_version": "2025-06-10", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, "supported_endpoints": [ @@ -4689,14 +4187,12 @@ }, "azure/o4-mini": { "cache_read_input_token_cost": 2.75e-07, - "display_name": "o4 Mini", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -4720,15 +4216,12 @@ }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, - "display_name": "o4 Mini", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-16", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -4739,40 +4232,30 @@ "supports_vision": true }, "azure/standard/1024-x-1024/dall-e-2": { - "display_name": "DALL-E 2", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3", - "model_vendor": "openai", "input_cost_per_pixel": 4.359e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0 }, "azure/text-embedding-3-large": { - "display_name": "Text Embedding 3 Large", - "model_vendor": "openai", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure", "max_input_tokens": 8191, @@ -4781,8 +4264,6 @@ "output_cost_per_token": 0.0 }, "azure/text-embedding-3-small": { - "display_name": "Text Embedding 3 Small", - "model_vendor": "openai", "deprecation_date": "2026-04-30", "input_cost_per_token": 2e-08, "litellm_provider": "azure", @@ -4792,9 +4273,6 @@ "output_cost_per_token": 0.0 }, "azure/text-embedding-ada-002": { - "display_name": "Text Embedding Ada 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, @@ -4803,39 +4281,30 @@ "output_cost_per_token": 0.0 }, "azure/speech/azure-tts": { - "display_name": "Azure TTS", - "input_cost_per_character": 1.5e-05, + "input_cost_per_character": 15e-06, "litellm_provider": "azure", "mode": "audio_speech", - "model_vendor": "microsoft", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "azure/speech/azure-tts-hd": { - "display_name": "Azure TTS HD", - "input_cost_per_character": 3e-05, + "input_cost_per_character": 30e-06, "litellm_provider": "azure", "mode": "audio_speech", - "model_vendor": "microsoft", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "azure/tts-1": { - "display_name": "TTS 1", "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", - "mode": "audio_speech", - "model_vendor": "openai" + "mode": "audio_speech" }, "azure/tts-1-hd": { - "display_name": "TTS 1 HD", "input_cost_per_character": 3e-05, "litellm_provider": "azure", - "mode": "audio_speech", - "model_vendor": "openai" + "mode": "audio_speech" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 5.5e-07, - "display_name": "GPT-4.1", "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", @@ -4843,8 +4312,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-14", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "supported_endpoints": [ @@ -4872,7 +4339,6 @@ "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 1.1e-07, - "display_name": "GPT-4.1 Mini", "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, "litellm_provider": "azure", @@ -4880,8 +4346,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-14", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "supported_endpoints": [ @@ -4909,7 +4373,6 @@ "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-08, - "display_name": "GPT-4.1 Nano", "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 6e-08, "litellm_provider": "azure", @@ -4917,8 +4380,6 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-14", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "supported_endpoints": [ @@ -4945,15 +4406,12 @@ "azure/us/gpt-4o-2024-08-06": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 1.375e-06, - "display_name": "GPT-4o", "input_cost_per_token": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-08-06", "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4965,15 +4423,12 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2026-03-01", "cache_creation_input_token_cost": 1.38e-06, - "display_name": "GPT-4o", "input_cost_per_token": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-11-20", "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4983,15 +4438,12 @@ }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, - "display_name": "GPT-4o Mini", "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-07-18", "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5003,7 +4455,6 @@ "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, - "display_name": "GPT-4o Mini Realtime Preview", "input_cost_per_audio_token": 1.1e-05, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure", @@ -5011,8 +4462,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-12-17", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, "supports_audio_input": true, @@ -5025,7 +4474,6 @@ "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, - "display_name": "GPT-4o Realtime Preview", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -5033,8 +4481,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-10-01", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, "supports_audio_input": true, @@ -5047,7 +4493,6 @@ "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, - "display_name": "GPT-4o Realtime Preview", "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -5055,8 +4500,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-12-17", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2.2e-05, "supported_modalities": [ @@ -5076,15 +4519,12 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, - "display_name": "GPT-5", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -5111,15 +4551,12 @@ }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, - "display_name": "GPT-5 Mini", "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 2.2e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -5146,15 +4583,12 @@ }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, - "display_name": "GPT-5 Nano", "input_cost_per_token": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-08-07", "output_cost_per_token": 4.4e-07, "supported_endpoints": [ "/v1/chat/completions", @@ -5181,14 +4615,12 @@ }, "azure/us/gpt-5.1": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -5216,14 +4648,12 @@ }, "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1 Chat", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -5251,14 +4681,12 @@ }, "azure/us/gpt-5.1-codex": { "cache_read_input_token_cost": 1.4e-07, - "display_name": "GPT-5.1 Codex", "input_cost_per_token": 1.38e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/responses" @@ -5283,14 +4711,12 @@ }, "azure/us/gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.8e-08, - "display_name": "GPT-5.1 Codex Mini", "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "model_vendor": "openai", "output_cost_per_token": 2.2e-06, "supported_endpoints": [ "/v1/responses" @@ -5315,15 +4741,12 @@ }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "display_name": "o1", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-12-17", "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5333,7 +4756,6 @@ }, "azure/us/o1-mini-2024-09-12": { "cache_read_input_token_cost": 6.05e-07, - "display_name": "o1 Mini", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -5341,8 +4763,6 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-09-12", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "supports_function_calling": true, @@ -5352,15 +4772,12 @@ }, "azure/us/o1-preview-2024-09-12": { "cache_read_input_token_cost": 8.25e-06, - "display_name": "o1 Preview", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "model_vendor": "openai", - "model_version": "2024-09-12", "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5370,15 +4787,12 @@ "azure/us/o3-2025-04-16": { "deprecation_date": "2026-04-16", "cache_read_input_token_cost": 5.5e-07, - "display_name": "o3", "input_cost_per_token": 2.2e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-16", "output_cost_per_token": 8.8e-06, "supported_endpoints": [ "/v1/chat/completions", @@ -5402,7 +4816,6 @@ }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "display_name": "o3 Mini", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -5410,8 +4823,6 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-01-31", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "supports_prompt_caching": true, @@ -5421,15 +4832,12 @@ }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.1e-07, - "display_name": "o4 Mini", "input_cost_per_token": 1.21e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "model_vendor": "openai", - "model_version": "2025-04-16", "output_cost_per_token": 4.84e-06, "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -5440,44 +4848,36 @@ "supports_vision": true }, "azure/whisper-1": { - "display_name": "Whisper", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", - "model_vendor": "openai", "output_cost_per_second": 0.0001 }, "azure_ai/Cohere-embed-v3-english": { - "display_name": "Cohere Embed v3 English", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", - "model_vendor": "cohere", "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": { - "display_name": "Cohere Embed v3 Multilingual", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", - "model_vendor": "cohere", "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": { - "display_name": "FLUX 1.1 Pro", "litellm_provider": "azure_ai", "mode": "image_generation", - "model_vendor": "black-forest-labs", "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": [ @@ -5485,10 +4885,8 @@ ] }, "azure_ai/FLUX.1-Kontext-pro": { - "display_name": "FLUX 1 Kontext Pro", "litellm_provider": "azure_ai", "mode": "image_generation", - "model_vendor": "black-forest-labs", "output_cost_per_image": 0.04, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ @@ -5496,14 +4894,12 @@ ] }, "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "display_name": "Llama 3.2 11B Vision", "input_cost_per_token": 3.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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, @@ -5511,14 +4907,12 @@ "supports_vision": true }, "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "display_name": "Llama 3.2 90B Vision", "input_cost_per_token": 2.04e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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, @@ -5526,28 +4920,24 @@ "supports_vision": true }, "azure_ai/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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": { - "display_name": "Llama 4 Maverick 17B", "input_cost_per_token": 1.41e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "meta", "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, @@ -5555,14 +4945,12 @@ "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "meta", "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, @@ -5570,191 +4958,163 @@ "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { - "display_name": "Llama 3 70B", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 3.7e-07, "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "display_name": "Llama 3.1 405B", "input_cost_per_token": 5.33e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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": { - "display_name": "Llama 3.1 70B", "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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": { - "display_name": "Llama 3.1 8B", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", "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": { - "display_name": "Phi 3 Medium 128K", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3 Medium 4K", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3 Mini 128K", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3 Mini 4K", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3 Small 128K", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3 Small 8K", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3.5 MoE", "input_cost_per_token": 1.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3.5 Mini", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 3.5 Vision", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "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", - "model_vendor": "microsoft", "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, @@ -5762,20 +5122,17 @@ "supports_vision": false }, "azure_ai/Phi-4-mini-instruct": { - "display_name": "Phi 4 Mini", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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": { - "display_name": "Phi 4 Multimodal", "input_cost_per_audio_token": 4e-06, "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", @@ -5783,7 +5140,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "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, @@ -5791,27 +5147,23 @@ "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "display_name": "Phi 4 Mini Reasoning", "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "output_cost_per_token": 3.2e-07, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { - "display_name": "Phi 4 Reasoning", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "microsoft", "output_cost_per_token": 5e-07, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, @@ -5819,66 +5171,54 @@ "supports_reasoning": true }, "azure_ai/mistral-document-ai-2505": { - "display_name": "Mistral Document AI", "litellm_provider": "azure_ai", + "ocr_cost_per_page": 3e-3, "mode": "ocr", - "model_vendor": "mistral", - "model_version": "2505", - "ocr_cost_per_page": 0.003, - "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry", "supported_endpoints": [ "/v1/ocr" - ] + ], + "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" }, "azure_ai/doc-intelligence/prebuilt-read": { - "display_name": "Document Intelligence Read", "litellm_provider": "azure_ai", + "ocr_cost_per_page": 1.5e-3, "mode": "ocr", - "model_vendor": "microsoft", - "ocr_cost_per_page": 0.0015, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supported_endpoints": [ "/v1/ocr" - ] + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/doc-intelligence/prebuilt-layout": { - "display_name": "Document Intelligence Layout", "litellm_provider": "azure_ai", + "ocr_cost_per_page": 1e-2, "mode": "ocr", - "model_vendor": "microsoft", - "ocr_cost_per_page": 0.01, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supported_endpoints": [ "/v1/ocr" - ] + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/doc-intelligence/prebuilt-document": { - "display_name": "Document Intelligence Document", "litellm_provider": "azure_ai", + "ocr_cost_per_page": 1e-2, "mode": "ocr", - "model_vendor": "microsoft", - "ocr_cost_per_page": 0.01, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "supported_endpoints": [ "/v1/ocr" - ] + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { - "display_name": "MAI 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", - "model_vendor": "microsoft", "output_cost_per_token": 5.4e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/cohere-rerank-v3-english": { - "display_name": "Cohere Rerank v3 English", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -5887,11 +5227,9 @@ "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", - "model_vendor": "cohere", "output_cost_per_token": 0.0 }, "azure_ai/cohere-rerank-v3-multilingual": { - "display_name": "Cohere Rerank v3 Multilingual", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -5900,11 +5238,9 @@ "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", - "model_vendor": "cohere", "output_cost_per_token": 0.0 }, "azure_ai/cohere-rerank-v3.5": { - "display_name": "Cohere Rerank v3.5", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -5913,13 +5249,9 @@ "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", - "model_vendor": "cohere", "output_cost_per_token": 0.0 }, "azure_ai/cohere-rerank-v4.0-pro": { - "display_name": "Cohere Rerank V4.0 Pro", - "model_vendor": "cohere", - "model_version": "4.0", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -5931,9 +5263,6 @@ "output_cost_per_token": 0.0 }, "azure_ai/cohere-rerank-v4.0-fast": { - "display_name": "Cohere Rerank V4.0 Fast", - "model_vendor": "cohere", - "model_version": "4.0", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -5944,10 +5273,7 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "azure_ai/deepseek-v3.2": { - "display_name": "Deepseek V3.2", - "model_vendor": "deepseek", - "model_version": "3.2", + "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 163840, @@ -5962,9 +5288,6 @@ "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { - "display_name": "Deepseek V3.2 Speciale", - "model_vendor": "deepseek", - "model_version": "3.2", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 163840, @@ -5979,55 +5302,46 @@ "supports_tool_choice": true }, "azure_ai/deepseek-r1": { - "display_name": "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", - "model_vendor": "deepseek", "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": { - "display_name": "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", - "model_vendor": "deepseek", "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": { - "display_name": "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", - "model_vendor": "deepseek", - "model_version": "0324", "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": { - "display_name": "Cohere Embed v4", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "embedding", - "model_vendor": "cohere", "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", @@ -6041,14 +5355,12 @@ "supports_embedding_image_input": true }, "azure_ai/global/grok-3": { - "display_name": "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", - "model_vendor": "xai", "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, @@ -6057,14 +5369,12 @@ "supports_web_search": true }, "azure_ai/global/grok-3-mini": { - "display_name": "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", - "model_vendor": "xai", "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, @@ -6074,14 +5384,12 @@ "supports_web_search": true }, "azure_ai/grok-3": { - "display_name": "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", - "model_vendor": "xai", "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, @@ -6090,14 +5398,12 @@ "supports_web_search": true }, "azure_ai/grok-3-mini": { - "display_name": "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", - "model_vendor": "xai", "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, @@ -6107,14 +5413,12 @@ "supports_web_search": true }, "azure_ai/grok-4": { - "display_name": "Grok 4", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "model_vendor": "xai", "output_cost_per_token": 2.75e-05, "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", "supports_function_calling": true, @@ -6123,30 +5427,26 @@ "supports_web_search": true }, "azure_ai/grok-4-fast-non-reasoning": { - "display_name": "Grok 4 Fast Non-Reasoning", - "input_cost_per_token": 4.3e-07, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "model_vendor": "xai", - "output_cost_per_token": 1.73e-06, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-fast-reasoning": { - "display_name": "Grok 4 Fast Reasoning", - "input_cost_per_token": 4.3e-07, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "model_vendor": "xai", - "output_cost_per_token": 1.73e-06, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701", "supports_function_calling": true, "supports_response_schema": true, @@ -6154,14 +5454,12 @@ "supports_web_search": true }, "azure_ai/grok-code-fast-1": { - "display_name": "Grok Code Fast 1", "input_cost_per_token": 3.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "model_vendor": "xai", "output_cost_per_token": 1.75e-05, "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", "supports_function_calling": true, @@ -6170,88 +5468,73 @@ "supports_web_search": true }, "azure_ai/jais-30b-chat": { - "display_name": "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", - "model_vendor": "g42", "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": { - "display_name": "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", - "model_vendor": "ai21", "output_cost_per_token": 7e-07, "supports_tool_choice": true }, "azure_ai/ministral-3b": { - "display_name": "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", - "model_vendor": "mistral", "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": { - "display_name": "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", - "model_vendor": "mistral", "output_cost_per_token": 1.2e-05, "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-large-2407": { - "display_name": "Mistral Large", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2407", "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": { - "display_name": "Mistral Large", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "mistral", "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-3": { - "display_name": "Mistral Large 3", - "model_vendor": "mistral", "input_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, @@ -6265,65 +5548,52 @@ "supports_vision": true }, "azure_ai/mistral-medium-2505": { - "display_name": "Mistral Medium", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2505", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-nemo": { - "display_name": "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", - "model_vendor": "mistral", "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": { - "display_name": "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", - "model_vendor": "mistral", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { - "display_name": "Mistral Small", "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2503", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "babbage-002": { - "display_name": "Babbage 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 4e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, @@ -6333,401 +5603,323 @@ "output_cost_per_token": 4e-07 }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { - "display_name": "Command Light", "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "cohere", "output_cost_per_second": 0.001902, "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { - "display_name": "Command", "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "cohere", "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { - "display_name": "Command Light", "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "cohere", "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { - "display_name": "Command", "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "cohere", "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.01475, "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0455 }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0455, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.008194, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.02527 }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.02527, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_token": 2.23e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 4.2e-06 }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 7.2e-07 }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 4.03e-06 }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 6.9e-07 }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.01635, "supports_tool_choice": true }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0415 }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0415, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "model_vendor": "anthropic", "mode": "chat", "output_cost_per_second": 0.009083, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.02305 }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.02305, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_token": 2.48e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05 }, "bedrock/eu-central-1/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 3.78e-06 }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 6.5e-07 }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 4.55e-06 }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 7.8e-07 }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { - "display_name": "Mistral 7B", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:2", "output_cost_per_token": 2.6e-07, "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { - "display_name": "Mistral Large", "input_cost_per_token": 1.04e-05, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2402-v1:0", "output_cost_per_token": 3.12e-05, "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { - "display_name": "Mixtral 8x7B", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:1", "output_cost_per_token": 9.1e-07, "supports_tool_choice": true }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -6737,8 +5929,6 @@ "notes": "Anthropic via Invoke route does not currently support pdf input." }, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_response_schema": true, @@ -6746,151 +5936,121 @@ "supports_vision": true }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 5.88e-06 }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 1.01e-06 }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0175 }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.00972 }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-v2:1": { - "display_name": "Claude 2.1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 3.5e-06 }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", - "model_vendor": "meta", - "model_version": "v1:0", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, @@ -6900,54 +6060,42 @@ "output_cost_per_token": 6e-07 }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { - "display_name": "Mistral 7B", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:2", "output_cost_per_token": 2e-07, "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { - "display_name": "Mistral Large", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2402-v1:0", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { - "display_name": "Mixtral 8x7B", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:1", "output_cost_per_token": 7e-07, "supports_tool_choice": true }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { - "display_name": "Nova Pro", "input_cost_per_token": 9.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -6956,72 +6104,57 @@ "supports_vision": true }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { - "display_name": "Titan Embed Text", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { - "display_name": "Titan Embed Text v2", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", - "model_version": "v2:0", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { - "display_name": "Titan Text Express", "input_cost_per_token": 1.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "model_vendor": "amazon", "output_cost_per_token": 1.7e-06 }, "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { - "display_name": "Titan Text Lite", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "model_vendor": "amazon", "output_cost_per_token": 4e-07 }, "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { - "display_name": "Titan Text Premier", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 1.5e-06 }, "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.8e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -7030,15 +6163,12 @@ "supports_vision": true }, "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude Haiku 3", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240307-v1:0", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -7047,15 +6177,12 @@ "supports_vision": true }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250929-v1:0", "output_cost_per_token": 1.65e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -7068,41 +6195,32 @@ "supports_vision": true }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true }, "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { - "display_name": "Nova Pro", "input_cost_per_token": 9.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -7111,74 +6229,59 @@ "supports_vision": true }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { - "display_name": "Titan Embed Text", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "display_name": "Titan Embed Text v2", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", - "model_vendor": "amazon", - "model_version": "v2:0", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "display_name": "Titan Text Express", "input_cost_per_token": 1.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "model_vendor": "amazon", "output_cost_per_token": 1.7e-06 }, "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { - "display_name": "Titan Text Lite", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "model_vendor": "amazon", "output_cost_per_token": 4e-07 }, "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { - "display_name": "Titan Text Premier", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "amazon", - "model_version": "v1:0", "output_cost_per_token": 1.5e-06 }, "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_read_input_token_cost": 3.6e-07, - "display_name": "Claude Sonnet 3.7", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250219-v1:0", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -7191,15 +6294,12 @@ "supports_vision": true }, "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620-v1:0", "output_cost_per_token": 1.8e-05, "supports_function_calling": true, "supports_pdf_input": true, @@ -7208,15 +6308,12 @@ "supports_vision": true }, "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude Haiku 3", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240307-v1:0", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_pdf_input": true, @@ -7225,15 +6322,12 @@ "supports_vision": true }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250929-v1:0", "output_cost_per_token": 1.65e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -7246,215 +6340,170 @@ "supports_vision": true }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true }, "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 3.5e-06 }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "meta", - "model_version": "v1:0", "output_cost_per_token": 6e-07 }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.0175 }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2", "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v2:1", "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_second": 0.00972 }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { - "display_name": "Claude 2", "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v2:1", "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-instant-v1": { - "display_name": "Claude Instant", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-v1": { - "display_name": "Claude 1", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-v2:1": { - "display_name": "Claude 2", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "v2:1", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { - "display_name": "Mistral 7B", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:2", "output_cost_per_token": 2e-07, "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { - "display_name": "Mistral Large", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "2402-v1:0", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { - "display_name": "Mixtral 8x7B", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "model_vendor": "mistral", - "model_version": "v0:1", "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, - "display_name": "Claude Haiku 3.5", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022-v1:0", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7464,53 +6513,45 @@ "supports_tool_choice": true }, "cerebras/llama-3.3-70b": { - "display_name": "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", - "model_vendor": "meta", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-70b": { - "display_name": "Llama 3.1 70B", "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-8b": { - "display_name": "Llama 3.1 8B", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/gpt-oss-120b": { - "display_name": "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", - "model_vendor": "openai", "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, @@ -7520,23 +6561,18 @@ "supports_tool_choice": true }, "cerebras/qwen-3-32b": { - "display_name": "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", - "model_vendor": "alibaba", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/zai-glm-4.6": { - "display_name": "Zai Glm 4.6", - "model_vendor": "zhipu", - "model_version": "4.6", "input_cost_per_token": 2.25e-06, "litellm_provider": "cerebras", "max_input_tokens": 128000, @@ -7550,7 +6586,6 @@ "supports_tool_choice": true }, "chat-bison": { - "display_name": "Chat Bison", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", @@ -7558,14 +6593,12 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "google", "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": { - "display_name": "Chat Bison 32K", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", @@ -7573,14 +6606,12 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "google", "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": { - "display_name": "Chat Bison 32K", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", @@ -7588,15 +6619,12 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "google", - "model_version": "002", "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": { - "display_name": "Chat Bison", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", @@ -7604,8 +6632,6 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "google", - "model_version": "001", "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", @@ -7613,7 +6639,6 @@ }, "chat-bison@002": { "deprecation_date": "2025-04-09", - "display_name": "Chat Bison", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", @@ -7621,33 +6646,27 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "google", - "model_version": "002", "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": { - "display_name": "Chat Dolphin", "input_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "model_vendor": "nlp_cloud", "output_cost_per_token": 5e-07 }, "chatgpt-4o-latest": { - "display_name": "ChatGPT-4o", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "openai", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -7657,20 +6676,29 @@ "supports_tool_choice": true, "supports_vision": true }, + "gpt-4o-transcribe-diarize": { + "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" + ] + }, "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", - "display_name": "Claude Haiku 3.5", "input_cost_per_token": 8e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022", "output_cost_per_token": 4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7692,14 +6720,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1e-07, "deprecation_date": "2025-10-01", - "display_name": "Claude Haiku 3.5", "input_cost_per_token": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7720,15 +6746,12 @@ "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, - "display_name": "Claude Haiku 4.5", "input_cost_per_token": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251001", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7744,14 +6767,12 @@ "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, - "display_name": "Claude Haiku 4.5", "input_cost_per_token": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7768,15 +6789,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240620", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7792,15 +6810,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-10-01", - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20241022", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7823,14 +6838,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", - "display_name": "Claude Sonnet 3.5", "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7853,15 +6866,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-02-19", - "display_name": "Claude Sonnet 3.7", "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250219", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7885,14 +6895,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", - "display_name": "Claude Sonnet 3.7", "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -7914,15 +6922,12 @@ "cache_creation_input_token_cost": 3e-07, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-08, - "display_name": "Claude Haiku 3", "input_cost_per_token": 2.5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240307", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7937,15 +6942,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2026-05-01", - "display_name": "Claude Opus 3", "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20240229", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7960,14 +6962,12 @@ "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2025-03-01", - "display_name": "Claude Opus 3", "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, @@ -7980,15 +6980,12 @@ "claude-4-opus-20250514": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, - "display_name": "Claude Opus 4", "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250514", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8011,7 +7008,6 @@ "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, - "display_name": "Claude Sonnet 4", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "litellm_provider": "anthropic", @@ -8019,8 +7015,6 @@ "max_output_tokens": 64000, "max_tokens": 1000000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250514", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "search_context_cost_per_query": { @@ -8042,7 +7036,6 @@ "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "display_name": "Claude Sonnet 4.5", "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, @@ -8053,7 +7046,6 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8074,7 +7066,6 @@ "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "display_name": "Claude Sonnet 4.5", "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, @@ -8085,8 +7076,6 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250929", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8106,9 +7095,6 @@ "tool_use_system_prompt_tokens": 346 }, "claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -8137,14 +7123,12 @@ "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, - "display_name": "Claude Opus 4.1", "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8166,16 +7150,13 @@ "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, - "deprecation_date": "2026-08-05", - "display_name": "Claude Opus 4.1", "input_cost_per_token": 1.5e-05, + "deprecation_date": "2026-08-05", "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250805", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8197,16 +7178,13 @@ "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, - "deprecation_date": "2026-05-14", - "display_name": "Claude Opus 4", "input_cost_per_token": 1.5e-05, + "deprecation_date": "2026-05-14", "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20250514", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8228,15 +7206,12 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "display_name": "Claude Opus 4.5", "input_cost_per_token": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", - "model_version": "20251101", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8258,14 +7233,12 @@ "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, - "display_name": "Claude Opus 4.5", "input_cost_per_token": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "model_vendor": "anthropic", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8284,9 +7257,6 @@ "tool_use_system_prompt_tokens": 159 }, "claude-sonnet-4-20250514": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", - "model_version": "20250514", "deprecation_date": "2026-05-14", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -8319,19 +7289,15 @@ "tool_use_system_prompt_tokens": 159 }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { - "display_name": "Llama 2 7B Chat", "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, "max_tokens": 3072, "mode": "chat", - "model_vendor": "meta", "output_cost_per_token": 1.923e-06 }, "cloudflare/@cf/meta/llama-2-7b-chat-int8": { - "display_name": "Llama 2 7B Chat", - "model_vendor": "meta", "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 2048, @@ -8341,9 +7307,6 @@ "output_cost_per_token": 1.923e-06 }, "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { - "display_name": "Mistral 7B Instruct v0.1", - "model_vendor": "mistral", - "model_version": "v0.1", "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 8192, @@ -8353,8 +7316,6 @@ "output_cost_per_token": 1.923e-06 }, "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { - "display_name": "CodeLlama 7B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 4096, @@ -8364,8 +7325,6 @@ "output_cost_per_token": 1.923e-06 }, "code-bison": { - "display_name": "Code Bison", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", @@ -8379,9 +7338,6 @@ "supports_tool_choice": true }, "code-bison-32k@002": { - "display_name": "Code Bison 32K", - "model_vendor": "google", - "model_version": "002", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", @@ -8394,8 +7350,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-bison32k": { - "display_name": "Code Bison 32K", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", @@ -8408,9 +7362,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-bison@001": { - "display_name": "Code Bison", - "model_vendor": "google", - "model_version": "001", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", @@ -8423,9 +7374,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-bison@002": { - "display_name": "Code Bison", - "model_vendor": "google", - "model_version": "002", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", @@ -8438,8 +7386,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko": { - "display_name": "Code Gecko", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, @@ -8450,8 +7396,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko-latest": { - "display_name": "Code Gecko", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, @@ -8462,9 +7406,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko@001": { - "display_name": "Code Gecko", - "model_vendor": "google", - "model_version": "001", "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, @@ -8475,9 +7416,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko@002": { - "display_name": "Code Gecko", - "model_vendor": "google", - "model_version": "002", "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, @@ -8488,8 +7426,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "codechat-bison": { - "display_name": "CodeChat Bison", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8503,8 +7439,6 @@ "supports_tool_choice": true }, "codechat-bison-32k": { - "display_name": "CodeChat Bison 32K", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8518,9 +7452,6 @@ "supports_tool_choice": true }, "codechat-bison-32k@002": { - "display_name": "CodeChat Bison 32K", - "model_vendor": "google", - "model_version": "002", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8534,9 +7465,6 @@ "supports_tool_choice": true }, "codechat-bison@001": { - "display_name": "CodeChat Bison", - "model_vendor": "google", - "model_version": "001", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8550,9 +7478,6 @@ "supports_tool_choice": true }, "codechat-bison@002": { - "display_name": "CodeChat Bison", - "model_vendor": "google", - "model_version": "002", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8566,8 +7491,6 @@ "supports_tool_choice": true }, "codechat-bison@latest": { - "display_name": "CodeChat Bison", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", @@ -8581,9 +7504,6 @@ "supports_tool_choice": true }, "codestral/codestral-2405": { - "display_name": "Codestral", - "model_vendor": "mistral", - "model_version": "2405", "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, @@ -8596,8 +7516,6 @@ "supports_tool_choice": true }, "codestral/codestral-latest": { - "display_name": "Codestral", - "model_vendor": "mistral", "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, @@ -8610,8 +7528,6 @@ "supports_tool_choice": true }, "codex-mini-latest": { - "display_name": "Codex Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 3.75e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "openai", @@ -8641,9 +7557,6 @@ "supports_vision": true }, "cohere.command-light-text-v14": { - "display_name": "Command Light", - "model_vendor": "cohere", - "model_version": "v14", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 4096, @@ -8654,9 +7567,6 @@ "supports_tool_choice": true }, "cohere.command-r-plus-v1:0": { - "display_name": "Command R+", - "model_vendor": "cohere", - "model_version": "v1:0", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -8667,9 +7577,6 @@ "supports_tool_choice": true }, "cohere.command-r-v1:0": { - "display_name": "Command R", - "model_vendor": "cohere", - "model_version": "v1:0", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -8680,9 +7587,6 @@ "supports_tool_choice": true }, "cohere.command-text-v14": { - "display_name": "Command", - "model_vendor": "cohere", - "model_version": "v14", "input_cost_per_token": 1.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 4096, @@ -8693,9 +7597,6 @@ "supports_tool_choice": true }, "cohere.embed-english-v3": { - "display_name": "Embed English v3", - "model_vendor": "cohere", - "model_version": "v3", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, @@ -8705,9 +7606,6 @@ "supports_embedding_image_input": true }, "cohere.embed-multilingual-v3": { - "display_name": "Embed Multilingual v3", - "model_vendor": "cohere", - "model_version": "v3", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, @@ -8717,9 +7615,6 @@ "supports_embedding_image_input": true }, "cohere.embed-v4:0": { - "display_name": "Embed v4", - "model_vendor": "cohere", - "model_version": "v4:0", "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -8730,9 +7625,6 @@ "supports_embedding_image_input": true }, "cohere/embed-v4.0": { - "display_name": "Embed v4", - "model_vendor": "cohere", - "model_version": "v4.0", "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, @@ -8743,9 +7635,6 @@ "supports_embedding_image_input": true }, "cohere.rerank-v3-5:0": { - "display_name": "Rerank v3.5", - "model_vendor": "cohere", - "model_version": "v3-5:0", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", @@ -8759,8 +7648,6 @@ "output_cost_per_token": 0.0 }, "command": { - "display_name": "Command", - "model_vendor": "cohere", "input_cost_per_token": 1e-06, "litellm_provider": "cohere", "max_input_tokens": 4096, @@ -8770,9 +7657,6 @@ "output_cost_per_token": 2e-06 }, "command-a-03-2025": { - "display_name": "Command A", - "model_vendor": "cohere", - "model_version": "03-2025", "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 256000, @@ -8784,8 +7668,6 @@ "supports_tool_choice": true }, "command-light": { - "display_name": "Command Light", - "model_vendor": "cohere", "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", "max_input_tokens": 4096, @@ -8796,8 +7678,6 @@ "supports_tool_choice": true }, "command-nightly": { - "display_name": "Command Nightly", - "model_vendor": "cohere", "input_cost_per_token": 1e-06, "litellm_provider": "cohere", "max_input_tokens": 4096, @@ -8807,8 +7687,6 @@ "output_cost_per_token": 2e-06 }, "command-r": { - "display_name": "Command R", - "model_vendor": "cohere", "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, @@ -8820,9 +7698,6 @@ "supports_tool_choice": true }, "command-r-08-2024": { - "display_name": "Command R", - "model_vendor": "cohere", - "model_version": "08-2024", "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, @@ -8834,8 +7709,6 @@ "supports_tool_choice": true }, "command-r-plus": { - "display_name": "Command R+", - "model_vendor": "cohere", "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, @@ -8847,9 +7720,6 @@ "supports_tool_choice": true }, "command-r-plus-08-2024": { - "display_name": "Command R+", - "model_vendor": "cohere", - "model_version": "08-2024", "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, @@ -8861,9 +7731,6 @@ "supports_tool_choice": true }, "command-r7b-12-2024": { - "display_name": "Command R 7B", - "model_vendor": "cohere", - "model_version": "12-2024", "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, @@ -8876,8 +7743,6 @@ "supports_tool_choice": true }, "computer-use-preview": { - "display_name": "Computer Use Preview", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 8192, @@ -8905,8 +7770,6 @@ "supports_vision": true }, "deepseek-chat": { - "display_name": "DeepSeek Chat", - "model_vendor": "deepseek", "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "deepseek", @@ -8928,8 +7791,6 @@ "supports_tool_choice": true }, "deepseek-reasoner": { - "display_name": "DeepSeek Reasoner", - "model_vendor": "deepseek", "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "deepseek", @@ -8952,8 +7813,6 @@ "supports_tool_choice": false }, "dashscope/qwen-coder": { - "display_name": "Qwen Coder", - "model_vendor": "alibaba", "input_cost_per_token": 3e-07, "litellm_provider": "dashscope", "max_input_tokens": 1000000, @@ -8967,8 +7826,6 @@ "supports_tool_choice": true }, "dashscope/qwen-flash": { - "display_name": "Qwen Flash", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, @@ -8998,9 +7855,6 @@ ] }, "dashscope/qwen-flash-2025-07-28": { - "display_name": "Qwen Flash", - "model_vendor": "alibaba", - "model_version": "2025-07-28", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, @@ -9030,8 +7884,6 @@ ] }, "dashscope/qwen-max": { - "display_name": "Qwen Max", - "model_vendor": "alibaba", "input_cost_per_token": 1.6e-06, "litellm_provider": "dashscope", "max_input_tokens": 30720, @@ -9045,8 +7897,6 @@ "supports_tool_choice": true }, "dashscope/qwen-plus": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, @@ -9060,9 +7910,6 @@ "supports_tool_choice": true }, "dashscope/qwen-plus-2025-01-25": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", - "model_version": "2025-01-25", "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, @@ -9076,9 +7923,6 @@ "supports_tool_choice": true }, "dashscope/qwen-plus-2025-04-28": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", - "model_version": "2025-04-28", "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, @@ -9093,9 +7937,6 @@ "supports_tool_choice": true }, "dashscope/qwen-plus-2025-07-14": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", - "model_version": "2025-07-14", "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, @@ -9110,9 +7951,6 @@ "supports_tool_choice": true }, "dashscope/qwen-plus-2025-07-28": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", - "model_version": "2025-07-28", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, @@ -9144,9 +7982,6 @@ ] }, "dashscope/qwen-plus-2025-09-11": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", - "model_version": "2025-09-11", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, @@ -9178,8 +8013,6 @@ ] }, "dashscope/qwen-plus-latest": { - "display_name": "Qwen Plus", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, @@ -9211,8 +8044,6 @@ ] }, "dashscope/qwen-turbo": { - "display_name": "Qwen Turbo", - "model_vendor": "alibaba", "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 129024, @@ -9227,9 +8058,6 @@ "supports_tool_choice": true }, "dashscope/qwen-turbo-2024-11-01": { - "display_name": "Qwen Turbo", - "model_vendor": "alibaba", - "model_version": "2024-11-01", "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, @@ -9243,9 +8071,6 @@ "supports_tool_choice": true }, "dashscope/qwen-turbo-2025-04-28": { - "display_name": "Qwen Turbo", - "model_vendor": "alibaba", - "model_version": "2025-04-28", "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, @@ -9260,8 +8085,6 @@ "supports_tool_choice": true }, "dashscope/qwen-turbo-latest": { - "display_name": "Qwen Turbo", - "model_vendor": "alibaba", "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, @@ -9276,8 +8099,6 @@ "supports_tool_choice": true }, "dashscope/qwen3-30b-a3b": { - "display_name": "Qwen3 30B A3B", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, @@ -9289,8 +8110,6 @@ "supports_tool_choice": true }, "dashscope/qwen3-coder-flash": { - "display_name": "Qwen3 Coder Flash", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, @@ -9340,9 +8159,6 @@ ] }, "dashscope/qwen3-coder-flash-2025-07-28": { - "display_name": "Qwen3 Coder Flash", - "model_vendor": "alibaba", - "model_version": "2025-07-28", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, @@ -9388,8 +8204,6 @@ ] }, "dashscope/qwen3-coder-plus": { - "display_name": "Qwen3 Coder Plus", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, @@ -9439,9 +8253,6 @@ ] }, "dashscope/qwen3-coder-plus-2025-07-22": { - "display_name": "Qwen3 Coder Plus", - "model_vendor": "alibaba", - "model_version": "2025-07-22", "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, @@ -9487,8 +8298,6 @@ ] }, "dashscope/qwen3-max-preview": { - "display_name": "Qwen3 Max Preview", - "model_vendor": "alibaba", "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, @@ -9526,8 +8335,6 @@ ] }, "dashscope/qwq-plus": { - "display_name": "QWQ Plus", - "model_vendor": "alibaba", "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", "max_input_tokens": 98304, @@ -9541,8 +8348,6 @@ "supports_tool_choice": true }, "databricks/databricks-bge-large-en": { - "display_name": "BGE Large EN", - "model_vendor": "baai", "input_cost_per_token": 1.0003e-07, "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", @@ -9558,8 +8363,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-claude-3-7-sonnet": { - "display_name": "Claude Sonnet 3.7", - "model_vendor": "anthropic", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -9579,8 +8382,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-haiku-4-5": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -9600,8 +8401,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-opus-4": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", "input_cost_per_token": 1.5000020000000002e-05, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", @@ -9621,8 +8420,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-opus-4-1": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", "input_cost_per_token": 1.5000020000000002e-05, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", @@ -9642,8 +8439,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-opus-4-5": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", @@ -9663,8 +8458,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -9684,8 +8477,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { - "display_name": "Claude Sonnet 4.1", - "model_vendor": "anthropic", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -9705,8 +8496,6 @@ "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-5": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -9726,8 +8515,6 @@ "supports_tool_choice": true }, "databricks/databricks-gemini-2-5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -9745,8 +8532,6 @@ "supports_tool_choice": true }, "databricks/databricks-gemini-2-5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -9764,8 +8549,6 @@ "supports_tool_choice": true }, "databricks/databricks-gemma-3-12b": { - "display_name": "Gemma 3 12B", - "model_vendor": "google", "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -9781,8 +8564,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-gpt-5": { - "display_name": "GPT-5", - "model_vendor": "openai", "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -9798,8 +8579,6 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-5-1": { - "display_name": "GPT-5.1", - "model_vendor": "openai", "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -9815,8 +8594,6 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-5-mini": { - "display_name": "GPT-5 Mini", - "model_vendor": "openai", "input_cost_per_token": 2.4997000000000006e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", @@ -9832,8 +8609,6 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-5-nano": { - "display_name": "GPT-5 Nano", - "model_vendor": "openai", "input_cost_per_token": 4.998e-08, "input_dbu_cost_per_token": 7.14e-07, "litellm_provider": "databricks", @@ -9849,8 +8624,6 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-oss-120b": { - "display_name": "GPT OSS 120B", - "model_vendor": "databricks", "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -9866,8 +8639,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-gpt-oss-20b": { - "display_name": "GPT OSS 20B", - "model_vendor": "databricks", "input_cost_per_token": 7e-08, "input_dbu_cost_per_token": 1e-06, "litellm_provider": "databricks", @@ -9883,8 +8654,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-gte-large-en": { - "display_name": "GTE Large EN", - "model_vendor": "alibaba", "input_cost_per_token": 1.2999000000000001e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", @@ -9900,8 +8669,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-llama-2-70b-chat": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -9918,8 +8685,6 @@ "supports_tool_choice": true }, "databricks/databricks-llama-4-maverick": { - "display_name": "Llama 4 Maverick", - "model_vendor": "meta", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -9936,8 +8701,6 @@ "supports_tool_choice": true }, "databricks/databricks-meta-llama-3-1-405b-instruct": { - "display_name": "Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", @@ -9954,8 +8717,6 @@ "supports_tool_choice": true }, "databricks/databricks-meta-llama-3-1-8b-instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -9971,8 +8732,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-meta-llama-3-3-70b-instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -9989,8 +8748,6 @@ "supports_tool_choice": true }, "databricks/databricks-meta-llama-3-70b-instruct": { - "display_name": "Llama 3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -10007,8 +8764,6 @@ "supports_tool_choice": true }, "databricks/databricks-mixtral-8x7b-instruct": { - "display_name": "Mixtral 8x7B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -10025,8 +8780,6 @@ "supports_tool_choice": true }, "databricks/databricks-mpt-30b-instruct": { - "display_name": "MPT 30B Instruct", - "model_vendor": "databricks", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -10043,8 +8796,6 @@ "supports_tool_choice": true }, "databricks/databricks-mpt-7b-instruct": { - "display_name": "MPT 7B Instruct", - "model_vendor": "databricks", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -10061,16 +8812,11 @@ "supports_tool_choice": true }, "dataforseo/search": { - "display_name": "DataForSEO Search", - "model_vendor": "dataforseo", "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", "mode": "search" }, "davinci-002": { - "display_name": "Davinci 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, @@ -10080,8 +8826,6 @@ "output_cost_per_token": 2e-06 }, "deepgram/base": { - "display_name": "Deepgram Base", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10096,8 +8840,6 @@ ] }, "deepgram/base-conversationalai": { - "display_name": "Deepgram Base Conversational AI", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10112,8 +8854,6 @@ ] }, "deepgram/base-finance": { - "display_name": "Deepgram Base Finance", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10128,8 +8868,6 @@ ] }, "deepgram/base-general": { - "display_name": "Deepgram Base General", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10144,8 +8882,6 @@ ] }, "deepgram/base-meeting": { - "display_name": "Deepgram Base Meeting", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10160,8 +8896,6 @@ ] }, "deepgram/base-phonecall": { - "display_name": "Deepgram Base Phone Call", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10176,8 +8910,6 @@ ] }, "deepgram/base-video": { - "display_name": "Deepgram Base Video", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10192,8 +8924,6 @@ ] }, "deepgram/base-voicemail": { - "display_name": "Deepgram Base Voicemail", - "model_vendor": "deepgram", "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { @@ -10208,8 +8938,6 @@ ] }, "deepgram/enhanced": { - "display_name": "Deepgram Enhanced", - "model_vendor": "deepgram", "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { @@ -10224,8 +8952,6 @@ ] }, "deepgram/enhanced-finance": { - "display_name": "Deepgram Enhanced Finance", - "model_vendor": "deepgram", "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { @@ -10240,8 +8966,6 @@ ] }, "deepgram/enhanced-general": { - "display_name": "Deepgram Enhanced General", - "model_vendor": "deepgram", "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { @@ -10256,8 +8980,6 @@ ] }, "deepgram/enhanced-meeting": { - "display_name": "Deepgram Enhanced Meeting", - "model_vendor": "deepgram", "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { @@ -10272,8 +8994,6 @@ ] }, "deepgram/enhanced-phonecall": { - "display_name": "Deepgram Enhanced Phone Call", - "model_vendor": "deepgram", "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { @@ -10288,8 +9008,6 @@ ] }, "deepgram/nova": { - "display_name": "Deepgram Nova", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10304,8 +9022,6 @@ ] }, "deepgram/nova-2": { - "display_name": "Deepgram Nova 2", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10320,8 +9036,6 @@ ] }, "deepgram/nova-2-atc": { - "display_name": "Deepgram Nova 2 ATC", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10336,8 +9050,6 @@ ] }, "deepgram/nova-2-automotive": { - "display_name": "Deepgram Nova 2 Automotive", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10352,8 +9064,6 @@ ] }, "deepgram/nova-2-conversationalai": { - "display_name": "Deepgram Nova 2 Conversational AI", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10368,8 +9078,6 @@ ] }, "deepgram/nova-2-drivethru": { - "display_name": "Deepgram Nova 2 Drive-Thru", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10384,8 +9092,6 @@ ] }, "deepgram/nova-2-finance": { - "display_name": "Deepgram Nova 2 Finance", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10400,8 +9106,6 @@ ] }, "deepgram/nova-2-general": { - "display_name": "Deepgram Nova 2 General", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10416,8 +9120,6 @@ ] }, "deepgram/nova-2-meeting": { - "display_name": "Deepgram Nova 2 Meeting", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10432,8 +9134,6 @@ ] }, "deepgram/nova-2-phonecall": { - "display_name": "Deepgram Nova 2 Phone Call", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10448,8 +9148,6 @@ ] }, "deepgram/nova-2-video": { - "display_name": "Deepgram Nova 2 Video", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10464,8 +9162,6 @@ ] }, "deepgram/nova-2-voicemail": { - "display_name": "Deepgram Nova 2 Voicemail", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10480,8 +9176,6 @@ ] }, "deepgram/nova-3": { - "display_name": "Deepgram Nova 3", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10496,8 +9190,6 @@ ] }, "deepgram/nova-3-general": { - "display_name": "Deepgram Nova 3 General", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10512,8 +9204,6 @@ ] }, "deepgram/nova-3-medical": { - "display_name": "Deepgram Nova 3 Medical", - "model_vendor": "deepgram", "input_cost_per_second": 8.667e-05, "litellm_provider": "deepgram", "metadata": { @@ -10528,8 +9218,6 @@ ] }, "deepgram/nova-general": { - "display_name": "Deepgram Nova General", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10544,8 +9232,6 @@ ] }, "deepgram/nova-phonecall": { - "display_name": "Deepgram Nova Phone Call", - "model_vendor": "deepgram", "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { @@ -10560,8 +9246,6 @@ ] }, "deepgram/whisper": { - "display_name": "Deepgram Whisper", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10575,8 +9259,6 @@ ] }, "deepgram/whisper-base": { - "display_name": "Deepgram Whisper Base", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10590,8 +9272,6 @@ ] }, "deepgram/whisper-large": { - "display_name": "Deepgram Whisper Large", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10605,8 +9285,6 @@ ] }, "deepgram/whisper-medium": { - "display_name": "Deepgram Whisper Medium", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10620,8 +9298,6 @@ ] }, "deepgram/whisper-small": { - "display_name": "Deepgram Whisper Small", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10635,8 +9311,6 @@ ] }, "deepgram/whisper-tiny": { - "display_name": "Deepgram Whisper Tiny", - "model_vendor": "deepgram", "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { @@ -10650,8 +9324,6 @@ ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { - "display_name": "MythoMax L2 13B", - "model_vendor": "gryphe", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -10662,8 +9334,6 @@ "supports_tool_choice": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "display_name": "Hermes 3 Llama 3.1 405B", - "model_vendor": "nousresearch", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10674,8 +9344,6 @@ "supports_tool_choice": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "display_name": "Hermes 3 Llama 3.1 70B", - "model_vendor": "nousresearch", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10686,8 +9354,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/QwQ-32B": { - "display_name": "QwQ 32B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10698,8 +9364,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "display_name": "Qwen 2.5 72B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -10710,8 +9374,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "display_name": "Qwen 2.5 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -10722,8 +9384,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "display_name": "Qwen 2.5 VL 32B Instruct", - "model_vendor": "alibaba", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -10735,8 +9395,6 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3-14B": { - "display_name": "Qwen 3 14B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -10747,8 +9405,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-235B-A22B": { - "display_name": "Qwen 3 235B A22B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -10759,9 +9415,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "display_name": "Qwen 3 235B A22B Instruct", - "model_vendor": "alibaba", - "model_version": "2507", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10772,9 +9425,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "display_name": "Qwen 3 235B A22B Thinking", - "model_vendor": "alibaba", - "model_version": "2507", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10785,8 +9435,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { - "display_name": "Qwen 3 30B A3B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -10797,8 +9445,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-32B": { - "display_name": "Qwen 3 32B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -10809,8 +9455,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "display_name": "Qwen 3 Coder 480B A35B Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10821,8 +9465,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "display_name": "Qwen 3 Coder 480B A35B Instruct Turbo", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10833,8 +9475,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "display_name": "Qwen 3 Next 80B A3B Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10845,8 +9485,6 @@ "supports_tool_choice": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "display_name": "Qwen 3 Next 80B A3B Thinking", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -10857,8 +9495,6 @@ "supports_tool_choice": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "display_name": "L3 8B Lunaris v1 Turbo", - "model_vendor": "sao10k", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -10869,8 +9505,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "display_name": "L3.1 70B Euryale v2.2", - "model_vendor": "sao10k", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10881,8 +9515,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "display_name": "L3.3 70B Euryale v2.3", - "model_vendor": "sao10k", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10893,8 +9525,6 @@ "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "display_name": "OLMoCR 7B", - "model_vendor": "allenai", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -10905,8 +9535,6 @@ "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, @@ -10918,8 +9546,6 @@ "supports_tool_choice": true }, "deepinfra/anthropic/claude-4-opus": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, @@ -10930,8 +9556,6 @@ "supports_tool_choice": true }, "deepinfra/anthropic/claude-4-sonnet": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, @@ -10942,8 +9566,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -10954,9 +9576,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -10968,9 +9587,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "display_name": "DeepSeek R1 0528 Turbo", - "model_vendor": "deepseek", - "model_version": "0528", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -10981,8 +9597,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -10993,8 +9607,6 @@ "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "display_name": "DeepSeek R1 Distill Qwen 32B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11005,8 +9617,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "display_name": "DeepSeek R1 Turbo", - "model_vendor": "deepseek", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -11017,8 +9627,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -11029,9 +9637,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", - "model_version": "0324", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -11042,8 +9647,6 @@ "supports_tool_choice": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "display_name": "DeepSeek V3.1", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -11056,8 +9659,6 @@ "supports_reasoning": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { - "display_name": "DeepSeek V3.1 Terminus", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -11069,8 +9670,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemini-2.0-flash-001": { - "display_name": "Gemini 2.0 Flash", - "model_vendor": "google", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -11081,8 +9680,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemini-2.5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -11093,8 +9690,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -11105,8 +9700,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemma-3-12b-it": { - "display_name": "Gemma 3 12B IT", - "model_vendor": "google", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11117,8 +9710,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemma-3-27b-it": { - "display_name": "Gemma 3 27B IT", - "model_vendor": "google", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11129,8 +9720,6 @@ "supports_tool_choice": true }, "deepinfra/google/gemma-3-4b-it": { - "display_name": "Gemma 3 4B IT", - "model_vendor": "google", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11141,8 +9730,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "display_name": "Llama 3.2 11B Vision Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11153,8 +9740,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11165,8 +9750,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11177,8 +9760,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "display_name": "Llama 3.3 70B Instruct Turbo", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11189,8 +9770,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "display_name": "Llama 4 Maverick 17B 128E Instruct", - "model_vendor": "meta", "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, @@ -11201,8 +9780,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, @@ -11213,8 +9790,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-Guard-3-8B": { - "display_name": "Llama Guard 3 8B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11225,8 +9800,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { - "display_name": "Llama Guard 4 12B", - "model_vendor": "meta", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -11237,8 +9810,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "display_name": "Meta Llama 3 8B Instruct", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -11249,8 +9820,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "display_name": "Meta Llama 3.1 70B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11261,8 +9830,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "display_name": "Meta Llama 3.1 70B Instruct Turbo", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11273,8 +9840,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "display_name": "Meta Llama 3.1 8B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11285,8 +9850,6 @@ "supports_tool_choice": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "display_name": "Meta Llama 3.1 8B Instruct Turbo", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11297,8 +9860,6 @@ "supports_tool_choice": true }, "deepinfra/microsoft/WizardLM-2-8x22B": { - "display_name": "WizardLM 2 8x22B", - "model_vendor": "microsoft", "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, @@ -11309,8 +9870,6 @@ "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { - "display_name": "Phi 4", - "model_vendor": "microsoft", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -11321,9 +9880,6 @@ "supports_tool_choice": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "display_name": "Mistral Nemo Instruct", - "model_vendor": "mistral", - "model_version": "2407", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11334,9 +9890,6 @@ "supports_tool_choice": true }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "display_name": "Mistral Small 24B Instruct", - "model_vendor": "mistral", - "model_version": "2501", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -11347,9 +9900,6 @@ "supports_tool_choice": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "display_name": "Mistral Small 3.2 24B Instruct", - "model_vendor": "mistral", - "model_version": "2506", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -11360,8 +9910,6 @@ "supports_tool_choice": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "display_name": "Mixtral 8x7B Instruct v0.1", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -11372,8 +9920,6 @@ "supports_tool_choice": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11384,9 +9930,6 @@ "supports_tool_choice": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { - "display_name": "Kimi K2 Instruct 0905", - "model_vendor": "moonshot", - "model_version": "0905", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -11398,8 +9941,6 @@ "supports_tool_choice": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "display_name": "Llama 3.1 Nemotron 70B Instruct", - "model_vendor": "nvidia", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11410,8 +9951,6 @@ "supports_tool_choice": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { - "display_name": "Llama 3.3 Nemotron Super 49B v1.5", - "model_vendor": "nvidia", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11422,8 +9961,6 @@ "supports_tool_choice": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { - "display_name": "NVIDIA Nemotron Nano 9B v2", - "model_vendor": "nvidia", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11434,8 +9971,6 @@ "supports_tool_choice": true }, "deepinfra/openai/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11446,8 +9981,6 @@ "supports_tool_choice": true }, "deepinfra/openai/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11458,8 +9991,6 @@ "supports_tool_choice": true }, "deepinfra/zai-org/GLM-4.5": { - "display_name": "GLM 4.5", - "model_vendor": "zhipu", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -11470,8 +10001,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-chat": { - "display_name": "DeepSeek Chat", - "model_vendor": "deepseek", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.7e-07, @@ -11488,8 +10017,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-coder": { - "display_name": "DeepSeek Coder", - "model_vendor": "deepseek", "input_cost_per_token": 1.4e-07, "input_cost_per_token_cache_hit": 1.4e-08, "litellm_provider": "deepseek", @@ -11504,8 +10031,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-r1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 5.5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "deepseek", @@ -11521,8 +10046,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-reasoner": { - "display_name": "DeepSeek Reasoner", - "model_vendor": "deepseek", "input_cost_per_token": 5.5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "deepseek", @@ -11538,8 +10061,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-v3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.7e-07, @@ -11556,9 +10077,6 @@ "supports_tool_choice": true }, "deepseek/deepseek-v3.2": { - "display_name": "DeepSeek V3.2", - "model_vendor": "deepseek", - "model_version": "v3.2", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -11574,8 +10092,6 @@ "supports_tool_choice": true }, "deepseek.v3-v1:0": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, @@ -11588,8 +10104,6 @@ "supports_tool_choice": true }, "dolphin": { - "display_name": "Dolphin", - "model_vendor": "nlp_cloud", "input_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, @@ -11599,8 +10113,6 @@ "output_cost_per_token": 5e-07 }, "doubao-embedding": { - "display_name": "Doubao Embedding", - "model_vendor": "volcengine", "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, @@ -11613,8 +10125,6 @@ "output_vector_size": 2560 }, "doubao-embedding-large": { - "display_name": "Doubao Embedding Large", - "model_vendor": "volcengine", "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, @@ -11627,9 +10137,6 @@ "output_vector_size": 2048 }, "doubao-embedding-large-text-240915": { - "display_name": "Doubao Embedding Large Text 240915", - "model_vendor": "volcengine", - "model_version": "240915", "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, @@ -11642,9 +10149,6 @@ "output_vector_size": 4096 }, "doubao-embedding-large-text-250515": { - "display_name": "Doubao Embedding Large Text 250515", - "model_vendor": "volcengine", - "model_version": "250515", "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, @@ -11657,9 +10161,6 @@ "output_vector_size": 2048 }, "doubao-embedding-text-240715": { - "display_name": "Doubao Embedding Text 240715", - "model_vendor": "volcengine", - "model_version": "240715", "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, @@ -11672,20 +10173,18 @@ "output_vector_size": 2560 }, "exa_ai/search": { - "display_name": "Exa AI Search", - "model_vendor": "exa_ai", "litellm_provider": "exa_ai", "mode": "search", "tiered_pricing": [ { - "input_cost_per_query": 0.005, + "input_cost_per_query": 5e-03, "max_results_range": [ 0, 25 ] }, { - "input_cost_per_query": 0.025, + "input_cost_per_query": 25e-03, "max_results_range": [ 26, 100 @@ -11694,76 +10193,74 @@ ] }, "firecrawl/search": { - "display_name": "Firecrawl Search", - "model_vendor": "firecrawl", "litellm_provider": "firecrawl", "mode": "search", "tiered_pricing": [ { - "input_cost_per_query": 0.00166, + "input_cost_per_query": 1.66e-03, "max_results_range": [ 1, 10 ] }, { - "input_cost_per_query": 0.00332, + "input_cost_per_query": 3.32e-03, "max_results_range": [ 11, 20 ] }, { - "input_cost_per_query": 0.00498, + "input_cost_per_query": 4.98e-03, "max_results_range": [ 21, 30 ] }, { - "input_cost_per_query": 0.00664, + "input_cost_per_query": 6.64e-03, "max_results_range": [ 31, 40 ] }, { - "input_cost_per_query": 0.0083, + "input_cost_per_query": 8.3e-03, "max_results_range": [ 41, 50 ] }, { - "input_cost_per_query": 0.00996, + "input_cost_per_query": 9.96e-03, "max_results_range": [ 51, 60 ] }, { - "input_cost_per_query": 0.01162, + "input_cost_per_query": 11.62e-03, "max_results_range": [ 61, 70 ] }, { - "input_cost_per_query": 0.01328, + "input_cost_per_query": 13.28e-03, "max_results_range": [ 71, 80 ] }, { - "input_cost_per_query": 0.01494, + "input_cost_per_query": 14.94e-03, "max_results_range": [ 81, 90 ] }, { - "input_cost_per_query": 0.0166, + "input_cost_per_query": 16.6e-03, "max_results_range": [ 91, 100 @@ -11775,15 +10272,11 @@ } }, "perplexity/search": { - "display_name": "Perplexity Search", - "model_vendor": "perplexity", - "input_cost_per_query": 0.005, + "input_cost_per_query": 5e-03, "litellm_provider": "perplexity", "mode": "search" }, "searxng/search": { - "display_name": "SearXNG Search", - "model_vendor": "searxng", "litellm_provider": "searxng", "mode": "search", "input_cost_per_query": 0.0, @@ -11792,8 +10285,6 @@ } }, "elevenlabs/scribe_v1": { - "display_name": "ElevenLabs Scribe v1", - "model_vendor": "elevenlabs", "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", "metadata": { @@ -11809,8 +10300,6 @@ ] }, "elevenlabs/scribe_v1_experimental": { - "display_name": "ElevenLabs Scribe v1 Experimental", - "model_vendor": "elevenlabs", "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", "metadata": { @@ -11826,8 +10315,6 @@ ] }, "embed-english-light-v2.0": { - "display_name": "Embed English Light v2.0", - "model_vendor": "cohere", "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 1024, @@ -11836,8 +10323,6 @@ "output_cost_per_token": 0.0 }, "embed-english-light-v3.0": { - "display_name": "Embed English Light v3.0", - "model_vendor": "cohere", "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 1024, @@ -11846,8 +10331,6 @@ "output_cost_per_token": 0.0 }, "embed-english-v2.0": { - "display_name": "Embed English v2.0", - "model_vendor": "cohere", "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 4096, @@ -11856,8 +10339,6 @@ "output_cost_per_token": 0.0 }, "embed-english-v3.0": { - "display_name": "Embed English v3.0", - "model_vendor": "cohere", "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, "litellm_provider": "cohere", @@ -11872,8 +10353,6 @@ "supports_image_input": true }, "embed-multilingual-v2.0": { - "display_name": "Embed Multilingual v2.0", - "model_vendor": "cohere", "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 768, @@ -11882,8 +10361,6 @@ "output_cost_per_token": 0.0 }, "embed-multilingual-v3.0": { - "display_name": "Embed Multilingual v3.0", - "model_vendor": "cohere", "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 1024, @@ -11893,9 +10370,7 @@ "supports_embedding_image_input": true }, "embed-multilingual-light-v3.0": { - "display_name": "Embed Multilingual Light v3.0", - "model_vendor": "cohere", - "input_cost_per_token": 0.0001, + "input_cost_per_token": 1e-04, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, @@ -11904,8 +10379,6 @@ "supports_embedding_image_input": true }, "eu.amazon.nova-lite-v1:0": { - "display_name": "Amazon Nova Lite", - "model_vendor": "amazon", "input_cost_per_token": 7.8e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -11920,8 +10393,6 @@ "supports_vision": true }, "eu.amazon.nova-micro-v1:0": { - "display_name": "Amazon Nova Micro", - "model_vendor": "amazon", "input_cost_per_token": 4.6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -11934,8 +10405,6 @@ "supports_response_schema": true }, "eu.amazon.nova-pro-v1:0": { - "display_name": "Amazon Nova Pro", - "model_vendor": "amazon", "input_cost_per_token": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -11951,9 +10420,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", - "model_version": "20241022", "input_cost_per_token": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -11969,9 +10435,6 @@ "supports_tool_choice": true }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, @@ -11995,9 +10458,6 @@ "tool_use_system_prompt_tokens": 346 }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240620", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12012,9 +10472,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "display_name": "Claude 3.5 Sonnet v2", - "model_vendor": "anthropic", - "model_version": "20241022", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12032,9 +10489,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", - "model_version": "20250219", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12053,9 +10507,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", - "model_version": "20240307", "input_cost_per_token": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12070,9 +10521,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-opus-20240229-v1:0": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12086,9 +10534,6 @@ "supports_vision": true }, "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "display_name": "Claude 3 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -12103,9 +10548,6 @@ "supports_vision": true }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", - "model_version": "20250805", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -12132,9 +10574,6 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-opus-4-20250514-v1:0": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -12161,9 +10600,6 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -12194,9 +10630,6 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 4.125e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, @@ -12227,8 +10660,6 @@ "tool_use_system_prompt_tokens": 346 }, "eu.meta.llama3-2-1b-instruct-v1:0": { - "display_name": "Llama 3.2 1B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -12240,8 +10671,6 @@ "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -12253,9 +10682,6 @@ "supports_tool_choice": false }, "eu.mistral.pixtral-large-2502-v1:0": { - "display_name": "Pixtral Large", - "model_vendor": "mistral", - "model_version": "2502", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -12267,8 +10693,6 @@ "supports_tool_choice": false }, "fal_ai/bria/text-to-image/3.2": { - "display_name": "Bria Text-to-Image 3.2", - "model_vendor": "bria", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, @@ -12277,9 +10701,6 @@ ] }, "fal_ai/fal-ai/flux-pro/v1.1": { - "display_name": "Flux Pro v1.1", - "model_vendor": "fal_ai", - "model_version": "1.1", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, @@ -12288,9 +10709,6 @@ ] }, "fal_ai/fal-ai/flux-pro/v1.1-ultra": { - "display_name": "Flux Pro v1.1 Ultra", - "model_vendor": "fal_ai", - "model_version": "1.1-ultra", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, @@ -12299,8 +10717,6 @@ ] }, "fal_ai/fal-ai/flux/schnell": { - "display_name": "Flux Schnell", - "model_vendor": "black_forest_labs", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.003, @@ -12309,8 +10725,6 @@ ] }, "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image": { - "display_name": "SeedReam v3", - "model_vendor": "bytedance", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, @@ -12319,8 +10733,6 @@ ] }, "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image": { - "display_name": "Dreamina v3.1", - "model_vendor": "bytedance", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, @@ -12329,8 +10741,6 @@ ] }, "fal_ai/fal-ai/ideogram/v3": { - "display_name": "Ideogram v3", - "model_vendor": "ideogram", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, @@ -12339,9 +10749,6 @@ ] }, "fal_ai/fal-ai/imagen4/preview": { - "display_name": "Imagen 4 Preview", - "model_vendor": "google", - "model_version": "4-preview", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, @@ -12350,9 +10757,6 @@ ] }, "fal_ai/fal-ai/imagen4/preview/fast": { - "display_name": "Imagen 4 Preview Fast", - "model_vendor": "google", - "model_version": "4-preview-fast", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, @@ -12361,9 +10765,6 @@ ] }, "fal_ai/fal-ai/imagen4/preview/ultra": { - "display_name": "Imagen 4 Preview Ultra", - "model_vendor": "google", - "model_version": "4-preview-ultra", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, @@ -12372,8 +10773,6 @@ ] }, "fal_ai/fal-ai/recraft/v3/text-to-image": { - "display_name": "Recraft v3", - "model_vendor": "recraft", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, @@ -12382,9 +10781,6 @@ ] }, "fal_ai/fal-ai/stable-diffusion-v35-medium": { - "display_name": "Stable Diffusion v3.5 Medium", - "model_vendor": "stability_ai", - "model_version": "3.5-medium", "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, @@ -12393,8 +10789,6 @@ ] }, "featherless_ai/featherless-ai/Qwerky-72B": { - "display_name": "Qwerky 72B", - "model_vendor": "featherless_ai", "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, @@ -12402,8 +10796,6 @@ "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { - "display_name": "Qwerky QwQ 32B", - "model_vendor": "featherless_ai", "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, @@ -12411,64 +10803,46 @@ "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { - "display_name": "Fireworks AI 4.1B-16B Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 2e-07 }, "fireworks-ai-56b-to-176b": { - "display_name": "Fireworks AI 56B-176B Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "output_cost_per_token": 1.2e-06 }, "fireworks-ai-above-16b": { - "display_name": "Fireworks AI Above 16B Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 9e-07 }, "fireworks-ai-default": { - "display_name": "Fireworks AI Default Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "output_cost_per_token": 0.0 }, "fireworks-ai-embedding-150m-to-350m": { - "display_name": "Fireworks AI Embedding 150M-350M Tier", - "model_vendor": "fireworks_ai", "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": { - "display_name": "Fireworks AI Embedding Up to 150M Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "output_cost_per_token": 0.0 }, "fireworks-ai-moe-up-to-56b": { - "display_name": "Fireworks AI MoE Up to 56B Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 5e-07 }, "fireworks-ai-up-to-4b": { - "display_name": "Fireworks AI Up to 4B Tier", - "model_vendor": "fireworks_ai", "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 2e-07 }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { - "display_name": "UAE Large V1", - "model_vendor": "whereisai", "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, @@ -12478,8 +10852,6 @@ "source": "https://fireworks.ai/pricing" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { - "display_name": "DeepSeek Coder V2 Instruct", - "model_vendor": "deepseek", "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, @@ -12493,8 +10865,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12507,9 +10877,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 160000, @@ -12522,8 +10889,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { - "display_name": "DeepSeek R1 Basic", - "model_vendor": "deepseek", "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12536,8 +10901,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12550,9 +10913,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", - "model_version": "0324", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, @@ -12565,8 +10925,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { - "display_name": "DeepSeek V3 Plus", - "model_vendor": "deepseek", "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12580,8 +10938,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus": { - "display_name": "DeepSeek V3 Plus Terminus", - "model_vendor": "deepseek", "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12595,15 +10951,13 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p2": { - "display_name": "DeepSeek V3p2", - "model_vendor": "deepseek", - "input_cost_per_token": 1.2e-06, + "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", "supports_function_calling": true, "supports_reasoning": true, @@ -12611,8 +10965,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/firefunction-v2": { - "display_name": "FireFunction V2", - "model_vendor": "fireworks_ai", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, @@ -12626,8 +10978,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p5": { - "display_name": "GLM-4 Plus", - "model_vendor": "zhipu", "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12642,9 +10992,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { - "display_name": "GLM-4 Plus Air", - "model_vendor": "zhipu", - "model_version": "4.5-air", "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12659,9 +11006,7 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p6": { - "display_name": "GLM-4.6", - "model_vendor": "zhipu", - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 0.55e-06, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, @@ -12675,8 +11020,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, @@ -12691,8 +11034,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 5e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, @@ -12707,8 +11048,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, @@ -12722,9 +11061,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905": { - "display_name": "Kimi K2 Instruct 0905", - "model_vendor": "moonshot", - "model_version": "0905", "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, @@ -12738,8 +11074,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking": { - "display_name": "Kimi K2 Thinking", - "model_vendor": "moonshot", "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, @@ -12754,8 +11088,6 @@ "supports_web_search": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { - "display_name": "Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, @@ -12769,8 +11101,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, @@ -12784,8 +11114,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { - "display_name": "Llama 3.2 11B Vision Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, @@ -12800,8 +11128,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { - "display_name": "Llama 3.2 1B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, @@ -12815,8 +11141,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, @@ -12830,8 +11154,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { - "display_name": "Llama 3.2 90B Vision Instruct", - "model_vendor": "meta", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, @@ -12845,8 +11167,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { - "display_name": "Llama 4 Maverick Instruct Basic", - "model_vendor": "meta", "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, @@ -12859,8 +11179,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { - "display_name": "Llama 4 Scout Instruct Basic", - "model_vendor": "meta", "input_cost_per_token": 1.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, @@ -12873,8 +11191,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { - "display_name": "Mixtral 8x22B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, @@ -12888,8 +11204,6 @@ "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { - "display_name": "Qwen 2 72B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, @@ -12903,8 +11217,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, @@ -12918,8 +11230,6 @@ "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/yi-large": { - "display_name": "Yi Large", - "model_vendor": "01_ai", "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, @@ -12933,8 +11243,6 @@ "supports_tool_choice": false }, "fireworks_ai/nomic-ai/nomic-embed-text-v1": { - "display_name": "Nomic Embed Text V1", - "model_vendor": "nomic", "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, @@ -12944,8 +11252,6 @@ "source": "https://fireworks.ai/pricing" }, "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { - "display_name": "Nomic Embed Text V1.5", - "model_vendor": "nomic", "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, @@ -12955,8 +11261,6 @@ "source": "https://fireworks.ai/pricing" }, "fireworks_ai/thenlper/gte-base": { - "display_name": "GTE Base", - "model_vendor": "thenlper", "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, @@ -12966,8 +11270,6 @@ "source": "https://fireworks.ai/pricing" }, "fireworks_ai/thenlper/gte-large": { - "display_name": "GTE Large", - "model_vendor": "thenlper", "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, @@ -12977,8 +11279,6 @@ "source": "https://fireworks.ai/pricing" }, "friendliai/meta-llama-3.1-70b-instruct": { - "display_name": "Llama 3.1 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6e-07, "litellm_provider": "friendliai", "max_input_tokens": 8192, @@ -12993,8 +11293,6 @@ "supports_tool_choice": true }, "friendliai/meta-llama-3.1-8b-instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "friendliai", "max_input_tokens": 8192, @@ -13009,9 +11307,6 @@ "supports_tool_choice": true }, "ft:babbage-002": { - "display_name": "Babbage 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 1.6e-06, "input_cost_per_token_batches": 2e-07, "litellm_provider": "text-completion-openai", @@ -13023,9 +11318,6 @@ "output_cost_per_token_batches": 2e-07 }, "ft:davinci-002": { - "display_name": "Davinci 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 1.2e-05, "input_cost_per_token_batches": 1e-06, "litellm_provider": "text-completion-openai", @@ -13037,8 +11329,6 @@ "output_cost_per_token_batches": 1e-06 }, "ft:gpt-3.5-turbo": { - "display_name": "GPT-3.5 Turbo Fine-tuned", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", @@ -13052,9 +11342,6 @@ "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0125": { - "display_name": "GPT-3.5 Turbo 0125 Fine-tuned", - "model_vendor": "openai", - "model_version": "0125", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -13066,9 +11353,6 @@ "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0613": { - "display_name": "GPT-3.5 Turbo 0613 Fine-tuned", - "model_vendor": "openai", - "model_version": "0613", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 4096, @@ -13080,9 +11364,6 @@ "supports_tool_choice": true }, "ft:gpt-3.5-turbo-1106": { - "display_name": "GPT-3.5 Turbo 1106 Fine-tuned", - "model_vendor": "openai", - "model_version": "1106", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -13094,9 +11375,6 @@ "supports_tool_choice": true }, "ft:gpt-4-0613": { - "display_name": "GPT-4 0613 Fine-tuned", - "model_vendor": "openai", - "model_version": "0613", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -13110,9 +11388,6 @@ "supports_tool_choice": true }, "ft:gpt-4o-2024-08-06": { - "display_name": "GPT-4o Fine-tuned", - "model_vendor": "openai", - "model_version": "2024-08-06", "cache_read_input_token_cost": 1.875e-06, "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 1.875e-06, @@ -13133,9 +11408,6 @@ "supports_vision": true }, "ft:gpt-4o-2024-11-20": { - "display_name": "GPT-4o Fine-tuned", - "model_vendor": "openai", - "model_version": "2024-11-20", "cache_creation_input_token_cost": 1.875e-06, "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", @@ -13153,9 +11425,6 @@ "supports_tool_choice": true }, "ft:gpt-4o-mini-2024-07-18": { - "display_name": "GPT-4o Mini Fine-tuned", - "model_vendor": "openai", - "model_version": "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, @@ -13175,9 +11444,6 @@ "supports_tool_choice": true }, "ft:gpt-4.1-2025-04-14": { - "display_name": "GPT-4.1 Fine-tuned", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 7.5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, @@ -13196,9 +11462,6 @@ "supports_tool_choice": true }, "ft:gpt-4.1-mini-2025-04-14": { - "display_name": "GPT-4.1 Mini Fine-tuned", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, @@ -13217,9 +11480,6 @@ "supports_tool_choice": true }, "ft:gpt-4.1-nano-2025-04-14": { - "display_name": "GPT-4.1 Nano Fine-tuned", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, @@ -13238,9 +11498,6 @@ "supports_tool_choice": true }, "ft:o4-mini-2025-04-16": { - "display_name": "O4 Mini Fine-tuned", - "model_vendor": "openai", - "model_version": "2025-04-16", "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, @@ -13259,8 +11516,6 @@ "supports_tool_choice": true }, "gemini-1.0-pro": { - "display_name": "Gemini 1.0 Pro", - "model_vendor": "google", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, @@ -13278,9 +11533,6 @@ "supports_tool_choice": true }, "gemini-1.0-pro-001": { - "display_name": "Gemini 1.0 Pro 001", - "model_vendor": "google", - "model_version": "1.0-001", "deprecation_date": "2025-04-09", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, @@ -13299,9 +11551,6 @@ "supports_tool_choice": true }, "gemini-1.0-pro-002": { - "display_name": "Gemini 1.0 Pro 002", - "model_vendor": "google", - "model_version": "1.0-002", "deprecation_date": "2025-04-09", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, @@ -13320,8 +11569,6 @@ "supports_tool_choice": true }, "gemini-1.0-pro-vision": { - "display_name": "Gemini 1.0 Pro Vision", - "model_vendor": "google", "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-vision-models", @@ -13340,9 +11587,6 @@ "supports_vision": true }, "gemini-1.0-pro-vision-001": { - "display_name": "Gemini 1.0 Pro Vision 001", - "model_vendor": "google", - "model_version": "1.0-001", "deprecation_date": "2025-04-09", "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, @@ -13362,9 +11606,6 @@ "supports_vision": true }, "gemini-1.0-ultra": { - "display_name": "Gemini 1.0 Ultra", - "model_vendor": "google", - "model_version": "1.0-ultra", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, @@ -13382,9 +11623,6 @@ "supports_tool_choice": true }, "gemini-1.0-ultra-001": { - "display_name": "Gemini 1.0 Ultra 001", - "model_vendor": "google", - "model_version": "1.0-ultra-001", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, @@ -13402,9 +11640,7 @@ "supports_tool_choice": true }, "gemini-1.5-flash": { - "display_name": "Gemini 1.5 Flash", - "model_vendor": "google", - "model_version": "1.5-flash", + "deprecation_date": "2025-09-29", "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, @@ -13439,9 +11675,6 @@ "supports_vision": true }, "gemini-1.5-flash-001": { - "display_name": "Gemini 1.5 Flash 001", - "model_vendor": "google", - "model_version": "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, @@ -13477,9 +11710,6 @@ "supports_vision": true }, "gemini-1.5-flash-002": { - "display_name": "Gemini 1.5 Flash 002", - "model_vendor": "google", - "model_version": "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, @@ -13515,9 +11745,7 @@ "supports_vision": true }, "gemini-1.5-flash-exp-0827": { - "display_name": "Gemini 1.5 Flash Exp 0827", - "model_vendor": "google", - "model_version": "1.5-flash-exp-0827", + "deprecation_date": "2025-09-29", "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, @@ -13552,9 +11780,7 @@ "supports_vision": true }, "gemini-1.5-flash-preview-0514": { - "display_name": "Gemini 1.5 Flash Preview 0514", - "model_vendor": "google", - "model_version": "1.5-flash-preview-0514", + "deprecation_date": "2025-09-29", "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, @@ -13588,9 +11814,7 @@ "supports_vision": true }, "gemini-1.5-pro": { - "display_name": "Gemini 1.5 Pro", - "model_vendor": "google", - "model_version": "1.5-pro", + "deprecation_date": "2025-09-29", "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, @@ -13620,9 +11844,6 @@ "supports_vision": true }, "gemini-1.5-pro-001": { - "display_name": "Gemini 1.5 Pro 001", - "model_vendor": "google", - "model_version": "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, @@ -13652,9 +11873,6 @@ "supports_vision": true }, "gemini-1.5-pro-002": { - "display_name": "Gemini 1.5 Pro 002", - "model_vendor": "google", - "model_version": "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, @@ -13684,9 +11902,7 @@ "supports_vision": true }, "gemini-1.5-pro-preview-0215": { - "display_name": "Gemini 1.5 Pro Preview 0215", - "model_vendor": "google", - "model_version": "1.5-pro-preview-0215", + "deprecation_date": "2025-09-29", "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, @@ -13714,9 +11930,7 @@ "supports_tool_choice": true }, "gemini-1.5-pro-preview-0409": { - "display_name": "Gemini 1.5 Pro Preview 0409", - "model_vendor": "google", - "model_version": "1.5-pro-preview-0409", + "deprecation_date": "2025-09-29", "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, @@ -13743,9 +11957,7 @@ "supports_tool_choice": true }, "gemini-1.5-pro-preview-0514": { - "display_name": "Gemini 1.5 Pro Preview 0514", - "model_vendor": "google", - "model_version": "1.5-pro-preview-0514", + "deprecation_date": "2025-09-29", "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, @@ -13773,9 +11985,6 @@ "supports_tool_choice": true }, "gemini-2.0-flash": { - "display_name": "Gemini 2.0 Flash", - "model_vendor": "google", - "model_version": "2.0-flash", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, @@ -13815,9 +12024,6 @@ "supports_web_search": true }, "gemini-2.0-flash-001": { - "display_name": "Gemini 2.0 Flash 001", - "model_vendor": "google", - "model_version": "2.0-flash-001", "cache_read_input_token_cost": 3.75e-08, "deprecation_date": "2026-02-05", "input_cost_per_audio_token": 1e-06, @@ -13856,8 +12062,6 @@ "supports_web_search": true }, "gemini-2.0-flash-exp": { - "display_name": "Gemini 2.0 Flash Experimental", - "model_vendor": "google", "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, @@ -13906,8 +12110,6 @@ "supports_web_search": true }, "gemini-2.0-flash-lite": { - "display_name": "Gemini 2.0 Flash Lite", - "model_vendor": "google", "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, @@ -13943,9 +12145,6 @@ "supports_web_search": true }, "gemini-2.0-flash-lite-001": { - "display_name": "Gemini 2.0 Flash Lite 001", - "model_vendor": "google", - "model_version": "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, @@ -13982,9 +12181,6 @@ "supports_web_search": true }, "gemini-2.0-flash-live-preview-04-09": { - "display_name": "Gemini 2.0 Flash Live Preview 04-09", - "model_vendor": "google", - "model_version": "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, @@ -14033,8 +12229,7 @@ "tpm": 250000 }, "gemini-2.0-flash-preview-image-generation": { - "display_name": "Gemini 2.0 Flash Preview Image Generation", - "model_vendor": "google", + "deprecation_date": "2025-11-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, @@ -14073,8 +12268,7 @@ "supports_web_search": true }, "gemini-2.0-flash-thinking-exp": { - "display_name": "Gemini 2.0 Flash Thinking Experimental", - "model_vendor": "google", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 0.0, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -14123,9 +12317,7 @@ "supports_web_search": true }, "gemini-2.0-flash-thinking-exp-01-21": { - "display_name": "Gemini 2.0 Flash Thinking Experimental 01-21", - "model_vendor": "google", - "model_version": "2.0-flash-thinking-exp-01-21", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 0.0, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -14175,9 +12367,6 @@ "supports_web_search": true }, "gemini-2.0-pro-exp-02-05": { - "display_name": "Gemini 2.0 Pro Experimental 02-05", - "model_vendor": "google", - "model_version": "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, @@ -14221,8 +12410,6 @@ "supports_web_search": true }, "gemini-2.5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -14268,8 +12455,6 @@ "supports_web_search": true }, "gemini-2.5-flash-image": { - "display_name": "Gemini 2.5 Flash Image", - "model_vendor": "google", "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -14285,6 +12470,7 @@ "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, @@ -14318,8 +12504,7 @@ "tpm": 8000000 }, "gemini-2.5-flash-image-preview": { - "display_name": "Gemini 2.5 Flash Image Preview", - "model_vendor": "google", + "deprecation_date": "2026-01-15", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -14335,6 +12520,7 @@ "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 3e-05, "output_cost_per_token": 3e-05, "rpm": 100000, @@ -14368,8 +12554,6 @@ "tpm": 8000000 }, "gemini-3-pro-image-preview": { - "display_name": "Gemini 3 Pro Image Preview", - "model_vendor": "google", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -14379,7 +12563,7 @@ "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token": 1.2e-04, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -14404,8 +12588,6 @@ "supports_web_search": true }, "gemini-2.5-flash-lite": { - "display_name": "Gemini 2.5 Flash Lite", - "model_vendor": "google", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, @@ -14451,9 +12633,6 @@ "supports_web_search": true }, "gemini-2.5-flash-lite-preview-09-2025": { - "display_name": "Gemini 2.5 Flash Lite Preview 09-2025", - "model_vendor": "google", - "model_version": "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, @@ -14499,9 +12678,6 @@ "supports_web_search": true }, "gemini-2.5-flash-preview-09-2025": { - "display_name": "Gemini 2.5 Flash Preview 09-2025", - "model_vendor": "google", - "model_version": "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, @@ -14547,9 +12723,6 @@ "supports_web_search": true }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { - "display_name": "Gemini Live 2.5 Flash Preview Native Audio 09-2025", - "model_vendor": "google", - "model_version": "live-2.5-flash-preview-native-audio-09-2025", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3e-07, @@ -14595,9 +12768,6 @@ "supports_web_search": true }, "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": { - "display_name": "Gemini Live 2.5 Flash Preview Native Audio 09-2025", - "model_vendor": "google", - "model_version": "live-2.5-flash-preview-native-audio-09-2025", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3e-07, @@ -14645,9 +12815,7 @@ "tpm": 8000000 }, "gemini-2.5-flash-lite-preview-06-17": { - "display_name": "Gemini 2.5 Flash Lite Preview 06-17", - "model_vendor": "google", - "model_version": "2.5-flash-lite-preview-06-17", + "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, @@ -14693,9 +12861,6 @@ "supports_web_search": true }, "gemini-2.5-flash-preview-04-17": { - "display_name": "Gemini 2.5 Flash Preview 04-17", - "model_vendor": "google", - "model_version": "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, @@ -14740,9 +12905,7 @@ "supports_web_search": true }, "gemini-2.5-flash-preview-05-20": { - "display_name": "Gemini 2.5 Flash Preview 05-20", - "model_vendor": "google", - "model_version": "2.5-flash-preview-05-20", + "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -14788,8 +12951,6 @@ "supports_web_search": true }, "gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "cache_read_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 1.25e-06, @@ -14834,8 +12995,6 @@ "supports_web_search": true }, "gemini-3-pro-preview": { - "display_name": "Gemini 3 Pro Preview", - "model_vendor": "google", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14884,8 +13043,6 @@ "supports_web_search": true }, "vertex_ai/gemini-3-pro-preview": { - "display_name": "Gemini 3 Pro Preview", - "model_vendor": "google", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14933,10 +13090,50 @@ "supports_vision": true, "supports_web_search": true }, + "vertex_ai/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "input_cost_per_audio_token": 1e-06, + "litellm_provider": "vertex_ai", + "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": 3e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini-2.5-pro-exp-03-25": { - "display_name": "Gemini 2.5 Pro Experimental 03-25", - "model_vendor": "google", - "model_version": "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, @@ -14980,9 +13177,7 @@ "supports_web_search": true }, "gemini-2.5-pro-preview-03-25": { - "display_name": "Gemini 2.5 Pro Preview 03-25", - "model_vendor": "google", - "model_version": "2.5-pro-preview-03-25", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -15028,9 +13223,7 @@ "supports_web_search": true }, "gemini-2.5-pro-preview-05-06": { - "display_name": "Gemini 2.5 Pro Preview 05-06", - "model_vendor": "google", - "model_version": "2.5-pro-preview-05-06", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -15079,9 +13272,6 @@ "supports_web_search": true }, "gemini-2.5-pro-preview-06-05": { - "display_name": "Gemini 2.5 Pro Preview 06-05", - "model_vendor": "google", - "model_version": "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, @@ -15127,8 +13317,6 @@ "supports_web_search": true }, "gemini-2.5-pro-preview-tts": { - "display_name": "Gemini 2.5 Pro Preview TTS", - "model_vendor": "google", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, @@ -15164,9 +13352,6 @@ "supports_web_search": true }, "gemini-embedding-001": { - "display_name": "Gemini Embedding 001", - "model_vendor": "google", - "model_version": "embedding-001", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, @@ -15177,8 +13362,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "gemini-flash-experimental": { - "display_name": "Gemini Flash Experimental", - "model_vendor": "google", "input_cost_per_character": 0, "input_cost_per_token": 0, "litellm_provider": "vertex_ai-language-models", @@ -15194,8 +13377,6 @@ "supports_tool_choice": true }, "gemini-pro": { - "display_name": "Gemini Pro", - "model_vendor": "google", "input_cost_per_character": 1.25e-07, "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, @@ -15213,8 +13394,6 @@ "supports_tool_choice": true }, "gemini-pro-experimental": { - "display_name": "Gemini Pro Experimental", - "model_vendor": "google", "input_cost_per_character": 0, "input_cost_per_token": 0, "litellm_provider": "vertex_ai-language-models", @@ -15230,8 +13409,6 @@ "supports_tool_choice": true }, "gemini-pro-vision": { - "display_name": "Gemini Pro Vision", - "model_vendor": "google", "input_cost_per_image": 0.0025, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-vision-models", @@ -15250,9 +13427,6 @@ "supports_vision": true }, "gemini/gemini-embedding-001": { - "display_name": "Gemini Embedding 001", - "model_vendor": "google", - "model_version": "embedding-001", "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, @@ -15265,8 +13439,7 @@ "tpm": 10000000 }, "gemini/gemini-1.5-flash": { - "display_name": "Gemini 1.5 Flash", - "model_vendor": "google", + "deprecation_date": "2025-09-29", "input_cost_per_token": 7.5e-08, "input_cost_per_token_above_128k_tokens": 1.5e-07, "litellm_provider": "gemini", @@ -15292,9 +13465,6 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-001": { - "display_name": "Gemini 1.5 Flash 001", - "model_vendor": "google", - "model_version": "1.5-flash-001", "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2025-05-24", @@ -15324,9 +13494,6 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-002": { - "display_name": "Gemini 1.5 Flash 002", - "model_vendor": "google", - "model_version": "1.5-flash-002", "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2025-09-24", @@ -15356,8 +13523,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-8b": { - "display_name": "Gemini 1.5 Flash 8B", - "model_vendor": "google", + "deprecation_date": "2025-09-29", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -15384,9 +13550,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-8b-exp-0827": { - "display_name": "Gemini 1.5 Flash 8B Experimental 0827", - "model_vendor": "google", - "model_version": "1.5-flash-8b-exp-0827", + "deprecation_date": "2025-09-29", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -15412,9 +13576,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-8b-exp-0924": { - "display_name": "Gemini 1.5 Flash 8B Experimental 0924", - "model_vendor": "google", - "model_version": "1.5-flash-8b-exp-0924", + "deprecation_date": "2025-09-29", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -15441,9 +13603,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-exp-0827": { - "display_name": "Gemini 1.5 Flash Experimental 0827", - "model_vendor": "google", - "model_version": "1.5-flash-exp-0827", + "deprecation_date": "2025-09-29", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -15469,8 +13629,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-flash-latest": { - "display_name": "Gemini 1.5 Flash Latest", - "model_vendor": "google", + "deprecation_date": "2025-09-29", "input_cost_per_token": 7.5e-08, "input_cost_per_token_above_128k_tokens": 1.5e-07, "litellm_provider": "gemini", @@ -15497,8 +13656,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro": { - "display_name": "Gemini 1.5 Pro", - "model_vendor": "google", + "deprecation_date": "2025-09-29", "input_cost_per_token": 3.5e-06, "input_cost_per_token_above_128k_tokens": 7e-06, "litellm_provider": "gemini", @@ -15518,9 +13676,6 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro-001": { - "display_name": "Gemini 1.5 Pro 001", - "model_vendor": "google", - "model_version": "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, @@ -15542,9 +13697,6 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro-002": { - "display_name": "Gemini 1.5 Pro 002", - "model_vendor": "google", - "model_version": "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, @@ -15566,9 +13718,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro-exp-0801": { - "display_name": "Gemini 1.5 Pro Experimental 0801", - "model_vendor": "google", - "model_version": "1.5-pro-exp-0801", + "deprecation_date": "2025-09-29", "input_cost_per_token": 3.5e-06, "input_cost_per_token_above_128k_tokens": 7e-06, "litellm_provider": "gemini", @@ -15588,9 +13738,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro-exp-0827": { - "display_name": "Gemini 1.5 Pro Experimental 0827", - "model_vendor": "google", - "model_version": "1.5-pro-exp-0827", + "deprecation_date": "2025-09-29", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -15610,8 +13758,7 @@ "tpm": 4000000 }, "gemini/gemini-1.5-pro-latest": { - "display_name": "Gemini 1.5 Pro Latest", - "model_vendor": "google", + "deprecation_date": "2025-09-29", "input_cost_per_token": 3.5e-06, "input_cost_per_token_above_128k_tokens": 7e-06, "litellm_provider": "gemini", @@ -15631,8 +13778,6 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash": { - "display_name": "Gemini 2.0 Flash", - "model_vendor": "google", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, @@ -15673,9 +13818,6 @@ "tpm": 10000000 }, "gemini/gemini-2.0-flash-001": { - "display_name": "Gemini 2.0 Flash 001", - "model_vendor": "google", - "model_version": "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, @@ -15714,8 +13856,6 @@ "tpm": 10000000 }, "gemini/gemini-2.0-flash-exp": { - "display_name": "Gemini 2.0 Flash Experimental", - "model_vendor": "google", "cache_read_input_token_cost": 0.0, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -15765,8 +13905,6 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash-lite": { - "display_name": "Gemini 2.0 Flash Lite", - "model_vendor": "google", "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, @@ -15803,9 +13941,7 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash-lite-preview-02-05": { - "display_name": "Gemini 2.0 Flash Lite Preview 02-05", - "model_vendor": "google", - "model_version": "2.0-flash-lite-preview-02-05", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, @@ -15843,9 +13979,7 @@ "tpm": 10000000 }, "gemini/gemini-2.0-flash-live-001": { - "display_name": "Gemini 2.0 Flash Live 001", - "model_vendor": "google", - "model_version": "2.0-flash-live-001", + "deprecation_date": "2025-12-09", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 2.1e-06, "input_cost_per_image": 2.1e-06, @@ -15894,8 +14028,7 @@ "tpm": 250000 }, "gemini/gemini-2.0-flash-preview-image-generation": { - "display_name": "Gemini 2.0 Flash Preview Image Generation", - "model_vendor": "google", + "deprecation_date": "2025-11-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, @@ -15935,8 +14068,7 @@ "tpm": 10000000 }, "gemini/gemini-2.0-flash-thinking-exp": { - "display_name": "Gemini 2.0 Flash Thinking Experimental", - "model_vendor": "google", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 0.0, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -15986,9 +14118,7 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash-thinking-exp-01-21": { - "display_name": "Gemini 2.0 Flash Thinking Experimental 01-21", - "model_vendor": "google", - "model_version": "2.0-flash-thinking-exp-01-21", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 0.0, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -16039,9 +14169,6 @@ "tpm": 4000000 }, "gemini/gemini-2.0-pro-exp-02-05": { - "display_name": "Gemini 2.0 Pro Experimental 02-05", - "model_vendor": "google", - "model_version": "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, @@ -16083,8 +14210,6 @@ "tpm": 1000000 }, "gemini/gemini-2.5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -16132,8 +14257,6 @@ "tpm": 8000000 }, "gemini/gemini-2.5-flash-image": { - "display_name": "Gemini 2.5 Flash Image", - "model_vendor": "google", "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -16150,6 +14273,7 @@ "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, @@ -16183,8 +14307,7 @@ "tpm": 8000000 }, "gemini/gemini-2.5-flash-image-preview": { - "display_name": "Gemini 2.5 Flash Image Preview", - "model_vendor": "google", + "deprecation_date": "2026-01-15", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -16200,6 +14323,7 @@ "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 3e-05, "output_cost_per_token": 3e-05, "rpm": 100000, @@ -16233,8 +14357,6 @@ "tpm": 8000000 }, "gemini/gemini-3-pro-image-preview": { - "display_name": "Gemini 3 Pro Image Preview", - "model_vendor": "google", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -16244,7 +14366,7 @@ "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token": 1.2e-04, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, @@ -16271,8 +14393,6 @@ "supports_web_search": true }, "gemini/gemini-2.5-flash-lite": { - "display_name": "Gemini 2.5 Flash Lite", - "model_vendor": "google", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, @@ -16320,9 +14440,6 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "display_name": "Gemini 2.5 Flash Lite Preview 09-2025", - "model_vendor": "google", - "model_version": "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, @@ -16370,9 +14487,6 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-preview-09-2025": { - "display_name": "Gemini 2.5 Flash Preview 09-2025", - "model_vendor": "google", - "model_version": "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, @@ -16420,8 +14534,6 @@ "tpm": 250000 }, "gemini/gemini-flash-latest": { - "display_name": "Gemini Flash Latest", - "model_vendor": "google", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -16469,8 +14581,6 @@ "tpm": 250000 }, "gemini/gemini-flash-lite-latest": { - "display_name": "Gemini Flash Lite Latest", - "model_vendor": "google", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, @@ -16518,9 +14628,7 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-lite-preview-06-17": { - "display_name": "Gemini 2.5 Flash Lite Preview 06-17", - "model_vendor": "google", - "model_version": "2.5-flash-lite-preview-06-17", + "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, @@ -16568,9 +14676,6 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-preview-04-17": { - "display_name": "Gemini 2.5 Flash Preview 04-17", - "model_vendor": "google", - "model_version": "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, @@ -16615,9 +14720,7 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-preview-05-20": { - "display_name": "Gemini 2.5 Flash Preview 05-20", - "model_vendor": "google", - "model_version": "2.5-flash-preview-05-20", + "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -16663,8 +14766,6 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-preview-tts": { - "display_name": "Gemini 2.5 Flash Preview TTS", - "model_vendor": "google", "cache_read_input_token_cost": 3.75e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1.5e-07, @@ -16705,8 +14806,6 @@ "tpm": 250000 }, "gemini/gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "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, @@ -16752,9 +14851,6 @@ "tpm": 800000 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { - "display_name": "Gemini 2.5 Computer Use Preview 10 2025", - "model_vendor": "google", - "model_version": "2.5", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", @@ -16786,8 +14882,6 @@ "tpm": 800000 }, "gemini/gemini-3-pro-preview": { - "display_name": "Gemini 3 Pro Preview", - "model_vendor": "google", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, @@ -16836,10 +14930,99 @@ "supports_web_search": true, "tpm": 800000 }, + "gemini/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 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": 3e-06, + "output_cost_per_token": 3e-06, + "rpm": 2000, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_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": 800000 + }, + "gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 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": 3e-06, + "output_cost_per_token": 3e-06, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_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/gemini-2.5-pro-exp-03-25": { - "display_name": "Gemini 2.5 Pro Experimental 03-25", - "model_vendor": "google", - "model_version": "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, @@ -16884,9 +15067,7 @@ "tpm": 250000 }, "gemini/gemini-2.5-pro-preview-03-25": { - "display_name": "Gemini 2.5 Pro Preview 03-25", - "model_vendor": "google", - "model_version": "2.5-pro-preview-03-25", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, @@ -16927,9 +15108,7 @@ "tpm": 10000000 }, "gemini/gemini-2.5-pro-preview-05-06": { - "display_name": "Gemini 2.5 Pro Preview 05-06", - "model_vendor": "google", - "model_version": "2.5-pro-preview-05-06", + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, @@ -16971,9 +15150,6 @@ "tpm": 10000000 }, "gemini/gemini-2.5-pro-preview-06-05": { - "display_name": "Gemini 2.5 Pro Preview 06-05", - "model_vendor": "google", - "model_version": "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, @@ -17015,8 +15191,6 @@ "tpm": 10000000 }, "gemini/gemini-2.5-pro-preview-tts": { - "display_name": "Gemini 2.5 Pro Preview TTS", - "model_vendor": "google", "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, @@ -17053,9 +15227,6 @@ "tpm": 10000000 }, "gemini/gemini-exp-1114": { - "display_name": "Gemini Experimental 1114", - "model_vendor": "google", - "model_version": "exp-1114", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -17085,9 +15256,6 @@ "tpm": 4000000 }, "gemini/gemini-exp-1206": { - "display_name": "Gemini Experimental 1206", - "model_vendor": "google", - "model_version": "exp-1206", "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", @@ -17117,8 +15285,6 @@ "tpm": 4000000 }, "gemini/gemini-gemma-2-27b-it": { - "display_name": "Gemma 2 27B IT", - "model_vendor": "google", "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, @@ -17131,8 +15297,6 @@ "supports_vision": true }, "gemini/gemini-gemma-2-9b-it": { - "display_name": "Gemma 2 9B IT", - "model_vendor": "google", "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, @@ -17145,8 +15309,6 @@ "supports_vision": true }, "gemini/gemini-pro": { - "display_name": "Gemini Pro", - "model_vendor": "google", "input_cost_per_token": 3.5e-07, "input_cost_per_token_above_128k_tokens": 7e-07, "litellm_provider": "gemini", @@ -17164,8 +15326,6 @@ "tpm": 120000 }, "gemini/gemini-pro-vision": { - "display_name": "Gemini Pro Vision", - "model_vendor": "google", "input_cost_per_token": 3.5e-07, "input_cost_per_token_above_128k_tokens": 7e-07, "litellm_provider": "gemini", @@ -17184,8 +15344,6 @@ "tpm": 120000 }, "gemini/gemma-3-27b-it": { - "display_name": "Gemma 3 27B IT", - "model_vendor": "google", "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, @@ -17214,63 +15372,43 @@ "supports_vision": true }, "gemini/imagen-3.0-fast-generate-001": { - "display_name": "Imagen 3.0 Fast Generate 001", - "model_vendor": "google", - "model_version": "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": { - "display_name": "Imagen 3.0 Generate 001", - "model_vendor": "google", - "model_version": "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": { - "display_name": "Imagen 3.0 Generate 002", - "model_vendor": "google", - "model_version": "3.0-generate-002", + "deprecation_date": "2025-11-10", "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": { - "display_name": "Imagen 4.0 Fast Generate 001", - "model_vendor": "google", - "model_version": "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": { - "display_name": "Imagen 4.0 Generate 001", - "model_vendor": "google", - "model_version": "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": { - "display_name": "Imagen 4.0 Ultra Generate 001", - "model_vendor": "google", - "model_version": "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": { - "display_name": "LearnLM 1.5 Pro Experimental", - "model_vendor": "google", - "model_version": "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, @@ -17299,9 +15437,6 @@ "supports_vision": true }, "gemini/veo-2.0-generate-001": { - "display_name": "Veo 2.0 Generate 001", - "model_vendor": "google", - "model_version": "2.0-generate-001", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -17316,9 +15451,7 @@ ] }, "gemini/veo-3.0-fast-generate-preview": { - "display_name": "Veo 3.0 Fast Generate Preview", - "model_vendor": "google", - "model_version": "3.0-fast-generate-preview", + "deprecation_date": "2025-11-12", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -17333,9 +15466,7 @@ ] }, "gemini/veo-3.0-generate-preview": { - "display_name": "Veo 3.0 Generate Preview", - "model_vendor": "google", - "model_version": "3.0-generate-preview", + "deprecation_date": "2025-11-12", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -17350,9 +15481,6 @@ ] }, "gemini/veo-3.1-fast-generate-preview": { - "display_name": "Veo 3.1 Fast Generate Preview", - "model_vendor": "google", - "model_version": "3.1-fast-generate-preview", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -17367,14 +15495,39 @@ ] }, "gemini/veo-3.1-generate-preview": { - "display_name": "Veo 3.1 Generate Preview", - "model_vendor": "google", - "model_version": "3.1-generate-preview", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", - "output_cost_per_second": 0.4, + "output_cost_per_second": 0.40, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.1-fast-generate-001": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.1-generate-001": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.40, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" @@ -17384,81 +15537,69 @@ ] }, "github_copilot/claude-haiku-4.5": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ - "/chat/completions" + "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/claude-opus-4.5": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ - "/chat/completions" + "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/claude-opus-41": { - "display_name": "Claude Opus 41", - "model_vendor": "anthropic", "litellm_provider": "github_copilot", "max_input_tokens": 80000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ - "/chat/completions" + "/v1/chat/completions" ], "supports_vision": true }, "github_copilot/claude-sonnet-4": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ - "/chat/completions" + "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/claude-sonnet-4.5": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ - "/chat/completions" + "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, @@ -17469,8 +15610,6 @@ "supports_vision": true }, "github_copilot/gemini-3-pro-preview": { - "display_name": "Gemini 3 Pro Preview", - "model_vendor": "google", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, @@ -17481,8 +15620,6 @@ "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { - "display_name": "GPT 3.5 Turbo", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, @@ -17491,8 +15628,6 @@ "supports_function_calling": true }, "github_copilot/gpt-3.5-turbo-0613": { - "display_name": "GPT 3.5 Turbo 0613", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, @@ -17501,8 +15636,6 @@ "supports_function_calling": true }, "github_copilot/gpt-4": { - "display_name": "GPT 4", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, @@ -17511,8 +15644,6 @@ "supports_function_calling": true }, "github_copilot/gpt-4-0613": { - "display_name": "GPT 4 0613", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, @@ -17521,8 +15652,6 @@ "supports_function_calling": true }, "github_copilot/gpt-4-o-preview": { - "display_name": "GPT 4 o Preview", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, @@ -17532,8 +15661,6 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { - "display_name": "GPT 4.1", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, @@ -17545,8 +15672,6 @@ "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { - "display_name": "GPT 4.1 2025 04 14", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, @@ -17558,14 +15683,10 @@ "supports_vision": true }, "github_copilot/gpt-41-copilot": { - "display_name": "GPT 41 Copilot", - "model_vendor": "openai", "litellm_provider": "github_copilot", "mode": "completion" }, "github_copilot/gpt-4o": { - "display_name": "GPT 4o", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, @@ -17576,8 +15697,6 @@ "supports_vision": true }, "github_copilot/gpt-4o-2024-05-13": { - "display_name": "GPT 4o 2024 05 13", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, @@ -17588,8 +15707,6 @@ "supports_vision": true }, "github_copilot/gpt-4o-2024-08-06": { - "display_name": "GPT 4o 2024 08 06", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, @@ -17599,8 +15716,6 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-4o-2024-11-20": { - "display_name": "GPT 4o 2024 11 20", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, @@ -17611,8 +15726,6 @@ "supports_vision": true }, "github_copilot/gpt-4o-mini": { - "display_name": "GPT 4o Mini", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, @@ -17622,8 +15735,6 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-4o-mini-2024-07-18": { - "display_name": "GPT 4o Mini 2024 07 18", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, @@ -17633,16 +15744,14 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-5": { - "display_name": "GPT 5", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ - "/chat/completions", - "/responses" + "/v1/chat/completions", + "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -17650,8 +15759,6 @@ "supports_vision": true }, "github_copilot/gpt-5-mini": { - "display_name": "GPT 5 Mini", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, @@ -17663,16 +15770,14 @@ "supports_vision": true }, "github_copilot/gpt-5.1": { - "display_name": "GPT 5.1", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supported_endpoints": [ - "/chat/completions", - "/responses" + "/v1/chat/completions", + "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -17680,15 +15785,13 @@ "supports_vision": true }, "github_copilot/gpt-5.1-codex-max": { - "display_name": "GPT 5.1 Codex Max", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ - "/responses" + "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -17696,16 +15799,14 @@ "supports_vision": true }, "github_copilot/gpt-5.2": { - "display_name": "GPT 5.2", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supported_endpoints": [ - "/chat/completions", - "/responses" + "/v1/chat/completions", + "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -17713,24 +15814,18 @@ "supports_vision": true }, "github_copilot/text-embedding-3-small": { - "display_name": "Text Embedding 3 Small", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { - "display_name": "Text Embedding 3 Small Inference", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { - "display_name": "Text Embedding Ada 002", - "model_vendor": "openai", "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, @@ -17799,8 +15894,6 @@ "output_vector_size": 2560 }, "google.gemma-3-12b-it": { - "display_name": "Gemma 3 12B It", - "model_vendor": "google", "input_cost_per_token": 9e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -17812,8 +15905,6 @@ "supports_vision": true }, "google.gemma-3-27b-it": { - "display_name": "Gemma 3 27B It", - "model_vendor": "google", "input_cost_per_token": 2.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -17825,8 +15916,6 @@ "supports_vision": true }, "google.gemma-3-4b-it": { - "display_name": "Gemma 3 4B It", - "model_vendor": "google", "input_cost_per_token": 4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -17838,16 +15927,11 @@ "supports_vision": true }, "google_pse/search": { - "display_name": "Google PSE Search", - "model_vendor": "google", "input_cost_per_query": 0.005, "litellm_provider": "google_pse", "mode": "search" }, "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -17878,9 +15962,6 @@ "tool_use_system_prompt_tokens": 346 }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -17911,9 +15992,6 @@ "tool_use_system_prompt_tokens": 159 }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, @@ -17936,9 +16014,6 @@ "tool_use_system_prompt_tokens": 346 }, "global.amazon.nova-2-lite-v1:0": { - "display_name": "Amazon.nova 2 Lite V1:0", - "model_vendor": "amazon", - "model_version": "0", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "bedrock_converse", @@ -17956,9 +16031,7 @@ "supports_vision": true }, "gpt-3.5-turbo": { - "display_name": "GPT-3.5 Turbo", - "model_vendor": "openai", - "input_cost_per_token": 5e-07, + "input_cost_per_token": 0.5e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, @@ -17971,9 +16044,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-0125": { - "display_name": "GPT-3.5 Turbo 0125", - "model_vendor": "openai", - "model_version": "0125", "input_cost_per_token": 5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -17988,9 +16058,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-0301": { - "display_name": "GPT-3.5 Turbo 0301", - "model_vendor": "openai", - "model_version": "0301", "input_cost_per_token": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 4097, @@ -18003,9 +16070,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-0613": { - "display_name": "GPT-3.5 Turbo 0613", - "model_vendor": "openai", - "model_version": "0613", "input_cost_per_token": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 4097, @@ -18019,9 +16083,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-1106": { - "display_name": "GPT-3.5 Turbo 1106", - "model_vendor": "openai", - "model_version": "1106", "deprecation_date": "2026-09-28", "input_cost_per_token": 1e-06, "litellm_provider": "openai", @@ -18037,8 +16098,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-16k": { - "display_name": "GPT-3.5 Turbo 16K", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -18051,9 +16110,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-16k-0613": { - "display_name": "GPT-3.5 Turbo 16K 0613", - "model_vendor": "openai", - "model_version": "0613", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -18066,8 +16122,6 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-instruct": { - "display_name": "GPT-3.5 Turbo Instruct", - "model_vendor": "openai", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, @@ -18077,9 +16131,6 @@ "output_cost_per_token": 2e-06 }, "gpt-3.5-turbo-instruct-0914": { - "display_name": "GPT-3.5 Turbo Instruct 0914", - "model_vendor": "openai", - "model_version": "0914", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, @@ -18089,8 +16140,6 @@ "output_cost_per_token": 2e-06 }, "gpt-4": { - "display_name": "GPT-4", - "model_vendor": "openai", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -18104,9 +16153,6 @@ "supports_tool_choice": true }, "gpt-4-0125-preview": { - "display_name": "GPT-4 0125 Preview", - "model_vendor": "openai", - "model_version": "0125-preview", "deprecation_date": "2026-03-26", "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -18122,9 +16168,6 @@ "supports_tool_choice": true }, "gpt-4-0314": { - "display_name": "GPT-4 0314", - "model_vendor": "openai", - "model_version": "0314", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -18137,9 +16180,6 @@ "supports_tool_choice": true }, "gpt-4-0613": { - "display_name": "GPT-4 0613", - "model_vendor": "openai", - "model_version": "0613", "deprecation_date": "2025-06-06", "input_cost_per_token": 3e-05, "litellm_provider": "openai", @@ -18154,9 +16194,6 @@ "supports_tool_choice": true }, "gpt-4-1106-preview": { - "display_name": "GPT-4 1106 Preview", - "model_vendor": "openai", - "model_version": "1106-preview", "deprecation_date": "2026-03-26", "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -18172,9 +16209,6 @@ "supports_tool_choice": true }, "gpt-4-1106-vision-preview": { - "display_name": "GPT-4 1106 Vision Preview", - "model_vendor": "openai", - "model_version": "1106-vision-preview", "deprecation_date": "2024-12-06", "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -18190,8 +16224,6 @@ "supports_vision": true }, "gpt-4-32k": { - "display_name": "GPT-4 32K", - "model_vendor": "openai", "input_cost_per_token": 6e-05, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -18204,9 +16236,6 @@ "supports_tool_choice": true }, "gpt-4-32k-0314": { - "display_name": "GPT-4 32K 0314", - "model_vendor": "openai", - "model_version": "0314", "input_cost_per_token": 6e-05, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -18219,9 +16248,6 @@ "supports_tool_choice": true }, "gpt-4-32k-0613": { - "display_name": "GPT-4 32K 0613", - "model_vendor": "openai", - "model_version": "0613", "input_cost_per_token": 6e-05, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -18234,8 +16260,6 @@ "supports_tool_choice": true }, "gpt-4-turbo": { - "display_name": "GPT-4 Turbo", - "model_vendor": "openai", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -18252,9 +16276,6 @@ "supports_vision": true }, "gpt-4-turbo-2024-04-09": { - "display_name": "GPT-4 Turbo", - "model_vendor": "openai", - "model_version": "2024-04-09", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -18271,8 +16292,6 @@ "supports_vision": true }, "gpt-4-turbo-preview": { - "display_name": "GPT-4 Turbo Preview", - "model_vendor": "openai", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -18288,8 +16307,6 @@ "supports_tool_choice": true }, "gpt-4-vision-preview": { - "display_name": "GPT-4 Vision Preview", - "model_vendor": "openai", "deprecation_date": "2024-12-06", "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -18305,8 +16322,6 @@ "supports_vision": true }, "gpt-4.1": { - "display_name": "GPT-4.1", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, @@ -18344,9 +16359,6 @@ "supports_vision": true }, "gpt-4.1-2025-04-14": { - "display_name": "GPT-4.1", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -18381,8 +16393,6 @@ "supports_vision": true }, "gpt-4.1-mini": { - "display_name": "GPT-4.1 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, @@ -18420,9 +16430,6 @@ "supports_vision": true }, "gpt-4.1-mini-2025-04-14": { - "display_name": "GPT-4.1 Mini", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, @@ -18457,8 +16464,6 @@ "supports_vision": true }, "gpt-4.1-nano": { - "display_name": "GPT-4.1 Nano", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 1e-07, @@ -18496,9 +16501,6 @@ "supports_vision": true }, "gpt-4.1-nano-2025-04-14": { - "display_name": "GPT-4.1 Nano", - "model_vendor": "openai", - "model_version": "2025-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -18533,8 +16535,6 @@ "supports_vision": true }, "gpt-4.5-preview": { - "display_name": "GPT-4.5 Preview", - "model_vendor": "openai", "cache_read_input_token_cost": 3.75e-05, "input_cost_per_token": 7.5e-05, "input_cost_per_token_batches": 3.75e-05, @@ -18555,9 +16555,6 @@ "supports_vision": true }, "gpt-4.5-preview-2025-02-27": { - "display_name": "GPT-4.5 Preview", - "model_vendor": "openai", - "model_version": "2025-02-27", "cache_read_input_token_cost": 3.75e-05, "deprecation_date": "2025-07-14", "input_cost_per_token": 7.5e-05, @@ -18579,8 +16576,6 @@ "supports_vision": true }, "gpt-4o": { - "display_name": "GPT-4o", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, "input_cost_per_token": 2.5e-06, @@ -18605,9 +16600,6 @@ "supports_vision": true }, "gpt-4o-2024-05-13": { - "display_name": "GPT-4o", - "model_vendor": "openai", - "model_version": "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, @@ -18628,9 +16620,6 @@ "supports_vision": true }, "gpt-4o-2024-08-06": { - "display_name": "GPT-4o", - "model_vendor": "openai", - "model_version": "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, @@ -18652,9 +16641,6 @@ "supports_vision": true }, "gpt-4o-2024-11-20": { - "display_name": "GPT-4o", - "model_vendor": "openai", - "model_version": "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, @@ -18676,8 +16662,6 @@ "supports_vision": true }, "gpt-4o-audio-preview": { - "display_name": "GPT-4o Audio Preview", - "model_vendor": "openai", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -18695,9 +16679,6 @@ "supports_tool_choice": true }, "gpt-4o-audio-preview-2024-10-01": { - "display_name": "GPT-4o Audio Preview", - "model_vendor": "openai", - "model_version": "2024-10-01", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -18715,9 +16696,6 @@ "supports_tool_choice": true }, "gpt-4o-audio-preview-2024-12-17": { - "display_name": "GPT-4o Audio Preview", - "model_vendor": "openai", - "model_version": "2024-12-17", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -18735,9 +16713,6 @@ "supports_tool_choice": true }, "gpt-4o-audio-preview-2025-06-03": { - "display_name": "GPT-4o Audio Preview", - "model_vendor": "openai", - "model_version": "2025-06-03", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -18755,8 +16730,6 @@ "supports_tool_choice": true }, "gpt-4o-mini": { - "display_name": "GPT-4o Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, "input_cost_per_token": 1.5e-07, @@ -18781,9 +16754,6 @@ "supports_vision": true }, "gpt-4o-mini-2024-07-18": { - "display_name": "GPT-4o Mini", - "model_vendor": "openai", - "model_version": "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, @@ -18810,8 +16780,6 @@ "supports_vision": true }, "gpt-4o-mini-audio-preview": { - "display_name": "GPT-4o Mini Audio Preview", - "model_vendor": "openai", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", @@ -18829,9 +16797,6 @@ "supports_tool_choice": true }, "gpt-4o-mini-audio-preview-2024-12-17": { - "display_name": "GPT-4o Mini Audio Preview", - "model_vendor": "openai", - "model_version": "2024-12-17", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", @@ -18849,8 +16814,6 @@ "supports_tool_choice": true }, "gpt-4o-mini-realtime-preview": { - "display_name": "GPT-4o Mini Realtime Preview", - "model_vendor": "openai", "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, "input_cost_per_audio_token": 1e-05, @@ -18870,9 +16833,6 @@ "supports_tool_choice": true }, "gpt-4o-mini-realtime-preview-2024-12-17": { - "display_name": "GPT-4o Mini Realtime Preview", - "model_vendor": "openai", - "model_version": "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, @@ -18892,8 +16852,6 @@ "supports_tool_choice": true }, "gpt-4o-mini-search-preview": { - "display_name": "GPT-4o Mini Search Preview", - "model_vendor": "openai", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, @@ -18920,9 +16878,6 @@ "supports_web_search": true }, "gpt-4o-mini-search-preview-2025-03-11": { - "display_name": "GPT-4o Mini Search Preview", - "model_vendor": "openai", - "model_version": "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, @@ -18943,8 +16898,6 @@ "supports_vision": true }, "gpt-4o-mini-transcribe": { - "display_name": "GPT-4o Mini Transcribe", - "model_vendor": "openai", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", @@ -18957,8 +16910,6 @@ ] }, "gpt-4o-mini-tts": { - "display_name": "GPT-4o Mini TTS", - "model_vendor": "openai", "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "mode": "audio_speech", @@ -18977,8 +16928,6 @@ ] }, "gpt-4o-realtime-preview": { - "display_name": "GPT-4o Realtime Preview", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, @@ -18997,9 +16946,6 @@ "supports_tool_choice": true }, "gpt-4o-realtime-preview-2024-10-01": { - "display_name": "GPT-4o Realtime Preview", - "model_vendor": "openai", - "model_version": "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, @@ -19019,9 +16965,6 @@ "supports_tool_choice": true }, "gpt-4o-realtime-preview-2024-12-17": { - "display_name": "GPT-4o Realtime Preview", - "model_vendor": "openai", - "model_version": "2024-12-17", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, @@ -19040,9 +16983,6 @@ "supports_tool_choice": true }, "gpt-4o-realtime-preview-2025-06-03": { - "display_name": "GPT-4o Realtime Preview", - "model_vendor": "openai", - "model_version": "2025-06-03", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, @@ -19061,8 +17001,6 @@ "supports_tool_choice": true }, "gpt-4o-search-preview": { - "display_name": "GPT-4o Search Preview", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, @@ -19089,9 +17027,6 @@ "supports_web_search": true }, "gpt-4o-search-preview-2025-03-11": { - "display_name": "GPT-4o Search Preview", - "model_vendor": "openai", - "model_version": "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, @@ -19112,8 +17047,6 @@ "supports_vision": true }, "gpt-4o-transcribe": { - "display_name": "GPT-4o Transcribe", - "model_vendor": "openai", "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -19125,9 +17058,367 @@ "/v1/audio/transcriptions" ] }, + "gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_token": 1e-05, + "input_cost_per_image_token": 8e-06, + "output_cost_per_image_token": 3.2e-05, + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_token": 1e-05, + "input_cost_per_image_token": 8e-06, + "output_cost_per_image_token": 3.2e-05, + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1024-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1024-x-1536/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1536-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1024-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.034, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1024-x-1536/gpt-image-1.5": { + "input_cost_per_image": 0.05, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1536-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.05, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1024-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.133, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1024-x-1536/gpt-image-1.5": { + "input_cost_per_image": 0.20, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1536-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.20, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1024-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1024-x-1536/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1536-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1024-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1024-x-1536/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1536-x-1024/gpt-image-1.5": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1024-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1024-x-1536/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "low/1536-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1024-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.034, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1024-x-1536/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.05, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "medium/1536-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.05, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1024-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.133, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1024-x-1536/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.20, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "high/1536-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.20, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1024-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1024-x-1536/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "standard/1536-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1024-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.009, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1024-x-1536/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "1536-x-1024/gpt-image-1.5-2025-12-16": { + "input_cost_per_image": 0.013, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, "gpt-5": { - "display_name": "GPT-5", - "model_vendor": "openai", "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, @@ -19167,8 +17458,6 @@ "supports_vision": true }, "gpt-5.1": { - "display_name": "GPT-5.1", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, @@ -19205,9 +17494,6 @@ "supports_vision": true }, "gpt-5.1-2025-11-13": { - "display_name": "GPT-5.1", - "model_vendor": "openai", - "model_version": "2025-11-13", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, @@ -19244,8 +17530,6 @@ "supports_vision": true }, "gpt-5.1-chat-latest": { - "display_name": "GPT-5.1 Chat Latest", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, @@ -19281,9 +17565,6 @@ "supports_vision": true }, "gpt-5.2": { - "display_name": "GPT 5.2", - "model_vendor": "openai", - "model_version": "5.2", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, @@ -19321,9 +17602,6 @@ "supports_vision": true }, "gpt-5.2-2025-12-11": { - "display_name": "GPT 5.2 2025 12 11", - "model_vendor": "openai", - "model_version": "2025-12-11", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, @@ -19361,9 +17639,6 @@ "supports_vision": true }, "gpt-5.2-chat-latest": { - "display_name": "GPT 5.2 Chat Latest", - "model_vendor": "openai", - "model_version": "5.2", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, @@ -19398,16 +17673,13 @@ "supports_vision": true }, "gpt-5.2-pro": { - "display_name": "GPT 5.2 Pro", - "model_vendor": "openai", - "model_version": "5.2", "input_cost_per_token": 2.1e-05, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 1.68e-04, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -19432,16 +17704,13 @@ "supports_web_search": true }, "gpt-5.2-pro-2025-12-11": { - "display_name": "GPT 5.2 Pro 2025 12 11", - "model_vendor": "openai", - "model_version": "2025-12-11", "input_cost_per_token": 2.1e-05, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 1.68e-04, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -19466,8 +17735,6 @@ "supports_web_search": true }, "gpt-5-pro": { - "display_name": "GPT-5 Pro", - "model_vendor": "openai", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", @@ -19475,7 +17742,7 @@ "max_output_tokens": 272000, "max_tokens": 272000, "mode": "responses", - "output_cost_per_token": 0.00012, + "output_cost_per_token": 1.2e-04, "output_cost_per_token_batches": 6e-05, "supported_endpoints": [ "/v1/batch", @@ -19501,9 +17768,6 @@ "supports_web_search": true }, "gpt-5-pro-2025-10-06": { - "display_name": "GPT-5 Pro", - "model_vendor": "openai", - "model_version": "2025-10-06", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", @@ -19511,7 +17775,7 @@ "max_output_tokens": 272000, "max_tokens": 272000, "mode": "responses", - "output_cost_per_token": 0.00012, + "output_cost_per_token": 1.2e-04, "output_cost_per_token_batches": 6e-05, "supported_endpoints": [ "/v1/batch", @@ -19537,9 +17801,6 @@ "supports_web_search": true }, "gpt-5-2025-08-07": { - "display_name": "GPT-5", - "model_vendor": "openai", - "model_version": "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, @@ -19579,8 +17840,6 @@ "supports_vision": true }, "gpt-5-chat": { - "display_name": "GPT-5 Chat", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", @@ -19613,8 +17872,6 @@ "supports_vision": true }, "gpt-5-chat-latest": { - "display_name": "GPT-5 Chat Latest", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", @@ -19647,8 +17904,6 @@ "supports_vision": true }, "gpt-5-codex": { - "display_name": "GPT-5 Codex", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", @@ -19679,8 +17934,6 @@ "supports_vision": true }, "gpt-5.1-codex": { - "display_name": "GPT-5.1 Codex", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, @@ -19714,9 +17967,6 @@ "supports_vision": true }, "gpt-5.1-codex-max": { - "display_name": "GPT 5.1 Codex Max", - "model_vendor": "openai", - "model_version": "5.1", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", @@ -19747,8 +17997,6 @@ "supports_vision": true }, "gpt-5.1-codex-mini": { - "display_name": "GPT-5.1 Codex Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, @@ -19782,8 +18030,6 @@ "supports_vision": true }, "gpt-5-mini": { - "display_name": "GPT-5 Mini", - "model_vendor": "openai", "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, @@ -19823,9 +18069,6 @@ "supports_vision": true }, "gpt-5-mini-2025-08-07": { - "display_name": "GPT-5 Mini", - "model_vendor": "openai", - "model_version": "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, @@ -19865,8 +18108,6 @@ "supports_vision": true }, "gpt-5-nano": { - "display_name": "GPT-5 Nano", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "input_cost_per_token": 5e-08, @@ -19903,9 +18144,6 @@ "supports_vision": true }, "gpt-5-nano-2025-08-07": { - "display_name": "GPT-5 Nano", - "model_vendor": "openai", - "model_version": "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, @@ -19941,23 +18179,19 @@ "supports_vision": true }, "gpt-image-1": { - "display_name": "GPT Image 1", - "model_vendor": "openai", - "input_cost_per_image": 0.042, - "input_cost_per_pixel": 4.0054321e-08, - "input_cost_per_token": 5e-06, + "cache_read_input_image_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1.25e-06, "input_cost_per_image_token": 1e-05, + "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_pixel": 0.0, - "output_cost_per_token": 4e-05, + "output_cost_per_image_token": 4e-05, "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini", - "model_vendor": "openai", "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "input_cost_per_image_token": 2.5e-06, @@ -19971,8 +18205,6 @@ ] }, "gpt-realtime": { - "display_name": "GPT Realtime", - "model_vendor": "openai", "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, @@ -20005,8 +18237,6 @@ "supports_tool_choice": true }, "gpt-realtime-mini": { - "display_name": "GPT Realtime Mini", - "model_vendor": "openai", "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "input_cost_per_audio_token": 1e-05, @@ -20038,9 +18268,6 @@ "supports_tool_choice": true }, "gpt-realtime-2025-08-28": { - "display_name": "GPT Realtime", - "model_vendor": "openai", - "model_version": "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, @@ -20073,8 +18300,6 @@ "supports_tool_choice": true }, "gradient_ai/alibaba-qwen3-32b": { - "display_name": "Qwen3 32B", - "model_vendor": "alibaba", "litellm_provider": "gradient_ai", "max_tokens": 2048, "mode": "chat", @@ -20087,8 +18312,6 @@ "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3-opus": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", "max_tokens": 1024, @@ -20103,8 +18326,6 @@ "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3.5-haiku": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", "max_tokens": 1024, @@ -20119,8 +18340,6 @@ "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3.5-sonnet": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", "max_tokens": 1024, @@ -20135,8 +18354,6 @@ "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3.7-sonnet": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", "max_tokens": 1024, @@ -20151,8 +18368,6 @@ "supports_tool_choice": false }, "gradient_ai/deepseek-r1-distill-llama-70b": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", "max_tokens": 8000, @@ -20167,8 +18382,6 @@ "supports_tool_choice": false }, "gradient_ai/llama3-8b-instruct": { - "display_name": "Llama 3 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", "max_tokens": 512, @@ -20183,8 +18396,6 @@ "supports_tool_choice": false }, "gradient_ai/llama3.3-70b-instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", "max_tokens": 2048, @@ -20199,8 +18410,6 @@ "supports_tool_choice": false }, "gradient_ai/mistral-nemo-instruct-2407": { - "display_name": "Mistral Nemo Instruct 2407", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", "max_tokens": 512, @@ -20215,8 +18424,6 @@ "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o": { - "display_name": "GPT-4o", - "model_vendor": "openai", "litellm_provider": "gradient_ai", "max_tokens": 16384, "mode": "chat", @@ -20229,8 +18436,6 @@ "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o-mini": { - "display_name": "GPT-4o Mini", - "model_vendor": "openai", "litellm_provider": "gradient_ai", "max_tokens": 16384, "mode": "chat", @@ -20243,8 +18448,6 @@ "supports_tool_choice": false }, "gradient_ai/openai-o3": { - "display_name": "o3", - "model_vendor": "openai", "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", "max_tokens": 100000, @@ -20259,8 +18462,6 @@ "supports_tool_choice": false }, "gradient_ai/openai-o3-mini": { - "display_name": "o3 Mini", - "model_vendor": "openai", "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", "max_tokens": 100000, @@ -20275,8 +18476,6 @@ "supports_tool_choice": false }, "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { - "display_name": "Qwen3 Coder 30B A3B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 262144, @@ -20289,8 +18488,6 @@ "supports_tool_choice": true }, "lemonade/gpt-oss-20b-mxfp4-GGUF": { - "display_name": "GPT OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 131072, @@ -20303,8 +18500,6 @@ "supports_tool_choice": true }, "lemonade/gpt-oss-120b-mxfp-GGUF": { - "display_name": "GPT OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 131072, @@ -20317,8 +18512,6 @@ "supports_tool_choice": true }, "lemonade/Gemma-3-4b-it-GGUF": { - "display_name": "Gemma 3 4B IT", - "model_vendor": "google", "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 128000, @@ -20331,8 +18524,6 @@ "supports_tool_choice": true }, "lemonade/Qwen3-4B-Instruct-2507-GGUF": { - "display_name": "Qwen3 4B Instruct 2507", - "model_vendor": "alibaba", "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 262144, @@ -20345,8 +18536,6 @@ "supports_tool_choice": true }, "amazon-nova/nova-micro-v1": { - "display_name": "Nova Micro V1", - "model_vendor": "amazon", "input_cost_per_token": 3.5e-08, "litellm_provider": "amazon_nova", "max_input_tokens": 128000, @@ -20359,8 +18548,6 @@ "supports_response_schema": true }, "amazon-nova/nova-lite-v1": { - "display_name": "Nova Lite V1", - "model_vendor": "amazon", "input_cost_per_token": 6e-08, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, @@ -20375,8 +18562,6 @@ "supports_vision": true }, "amazon-nova/nova-premier-v1": { - "display_name": "Nova Premier V1", - "model_vendor": "amazon", "input_cost_per_token": 2.5e-06, "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, @@ -20391,8 +18576,6 @@ "supports_vision": true }, "amazon-nova/nova-pro-v1": { - "display_name": "Nova Pro V1", - "model_vendor": "amazon", "input_cost_per_token": 8e-07, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, @@ -20406,90 +18589,7 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/deepseek-r1-distill-llama-70b": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", - "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": false, - "supports_tool_choice": true - }, - "groq/distil-whisper-large-v3-en": { - "display_name": "Distil Whisper Large V3 EN", - "model_vendor": "openai", - "input_cost_per_second": 5.56e-06, - "litellm_provider": "groq", - "mode": "audio_transcription", - "output_cost_per_second": 0.0 - }, - "groq/gemma-7b-it": { - "display_name": "Gemma 7B IT", - "model_vendor": "google", - "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": false, - "supports_tool_choice": true - }, - "groq/gemma2-9b-it": { - "display_name": "Gemma 2 9B IT", - "model_vendor": "google", - "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": false, - "supports_tool_choice": false - }, - "groq/llama-3.1-405b-reasoning": { - "display_name": "Llama 3.1 405B Reasoning", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama-3.1-70b-versatile": { - "display_name": "Llama 3.1 70B Versatile", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, "groq/llama-3.1-8b-instant": { - "display_name": "Llama 3.1 8B Instant", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "groq", "max_input_tokens": 128000, @@ -20501,114 +18601,7 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-3.2-11b-text-preview": { - "display_name": "Llama 3.2 11B Text Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-11b-vision-preview": { - "display_name": "Llama 3.2 11B Vision Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.2-1b-preview": { - "display_name": "Llama 3.2 1B Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-3b-preview": { - "display_name": "Llama 3.2 3B Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-text-preview": { - "display_name": "Llama 3.2 90B Text Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-vision-preview": { - "display_name": "Llama 3.2 90B Vision Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.3-70b-specdec": { - "display_name": "Llama 3.3 70B SpecDec", - "model_vendor": "meta", - "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": { - "display_name": "Llama 3.3 70B Versatile", - "model_vendor": "meta", "input_cost_per_token": 5.9e-07, "litellm_provider": "groq", "max_input_tokens": 128000, @@ -20620,9 +18613,19 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-guard-3-8b": { - "display_name": "Llama Guard 3 8B", - "model_vendor": "meta", + "groq/gemma-7b-it": { + "input_cost_per_token": 5e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-guard-4-12b": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, @@ -20631,53 +18634,7 @@ "mode": "chat", "output_cost_per_token": 2e-07 }, - "groq/llama2-70b-4096": { - "display_name": "Llama 2 70B", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-70b-8192-tool-use-preview": { - "display_name": "Llama 3 Groq 70B Tool Use Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-8b-8192-tool-use-preview": { - "display_name": "Llama 3 Groq 8B Tool Use Preview", - "model_vendor": "meta", - "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": false, - "supports_tool_choice": true - }, "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "display_name": "Llama 4 Maverick 17B 128E Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 131072, @@ -20687,11 +18644,10 @@ "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.1e-07, "litellm_provider": "groq", "max_input_tokens": 131072, @@ -20701,55 +18657,13 @@ "output_cost_per_token": 3.4e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/mistral-saba-24b": { - "display_name": "Mistral Saba 24B", - "model_vendor": "mistralai", - "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": { - "display_name": "Mixtral 8x7B", - "model_vendor": "mistralai", - "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": false, - "supports_tool_choice": true - }, - "groq/moonshotai/kimi-k2-instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", - "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 + "supports_tool_choice": true, + "supports_vision": true }, "groq/moonshotai/kimi-k2-instruct-0905": { - "display_name": "Kimi K2 Instruct 0905", - "model_vendor": "moonshot", - "model_version": "0905", "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost": 0.5e-06, "litellm_provider": "groq", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -20760,8 +18674,6 @@ "supports_tool_choice": true }, "groq/openai/gpt-oss-120b": { - "display_name": "GPT OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "groq", "max_input_tokens": 131072, @@ -20777,8 +18689,6 @@ "supports_web_search": true }, "groq/openai/gpt-oss-20b": { - "display_name": "GPT OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 1e-07, "litellm_provider": "groq", "max_input_tokens": 131072, @@ -20794,8 +18704,6 @@ "supports_web_search": true }, "groq/playai-tts": { - "display_name": "PlayAI TTS", - "model_vendor": "playai", "input_cost_per_character": 5e-05, "litellm_provider": "groq", "max_input_tokens": 10000, @@ -20804,8 +18712,6 @@ "mode": "audio_speech" }, "groq/qwen/qwen3-32b": { - "display_name": "Qwen 3 32B", - "model_vendor": "alibaba", "input_cost_per_token": 2.9e-07, "litellm_provider": "groq", "max_input_tokens": 131000, @@ -20819,50 +18725,36 @@ "supports_tool_choice": true }, "groq/whisper-large-v3": { - "display_name": "Whisper Large V3", - "model_vendor": "openai", - "model_version": "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": { - "display_name": "Whisper Large V3 Turbo", - "model_vendor": "openai", - "model_version": "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": { - "display_name": "DALL-E 3 HD 1024x1024", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 HD 1024x1792", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 HD 1792x1024", - "model_vendor": "openai", "input_cost_per_pixel": 6.539e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0 }, "heroku/claude-3-5-haiku": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", "litellm_provider": "heroku", "max_tokens": 4096, "mode": "chat", @@ -20871,8 +18763,6 @@ "supports_tool_choice": true }, "heroku/claude-3-5-sonnet-latest": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", @@ -20881,8 +18771,6 @@ "supports_tool_choice": true }, "heroku/claude-3-7-sonnet": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", @@ -20891,8 +18779,6 @@ "supports_tool_choice": true }, "heroku/claude-4-sonnet": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", @@ -20901,8 +18787,6 @@ "supports_tool_choice": true }, "high/1024-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 High 1024x1024", - "model_vendor": "openai", "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "openai", @@ -20913,8 +18797,6 @@ ] }, "high/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 High 1024x1536", - "model_vendor": "openai", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -20925,8 +18807,6 @@ ] }, "high/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 High 1536x1024", - "model_vendor": "openai", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -20937,8 +18817,6 @@ ] }, "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { - "display_name": "Hermes 3 Llama 3.1 70B", - "model_vendor": "nousresearch", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -20952,8 +18830,6 @@ "supports_tool_choice": true }, "hyperbolic/Qwen/QwQ-32B": { - "display_name": "QwQ 32B", - "model_vendor": "alibaba", "input_cost_per_token": 2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -20967,8 +18843,6 @@ "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { - "display_name": "Qwen 2.5 72B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -20982,8 +18856,6 @@ "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -20997,8 +18869,6 @@ "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen3-235B-A22B": { - "display_name": "Qwen 3 235B A22B", - "model_vendor": "alibaba", "input_cost_per_token": 2e-06, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -21012,8 +18882,6 @@ "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-R1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 4e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21027,9 +18895,6 @@ "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "input_cost_per_token": 2.5e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -21043,8 +18908,6 @@ "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-V3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "input_cost_per_token": 2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21058,9 +18921,6 @@ "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", - "model_version": "0324", "input_cost_per_token": 4e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21074,8 +18934,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21089,8 +18947,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -21104,8 +18960,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { - "display_name": "Meta Llama 3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -21119,8 +18973,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "display_name": "Meta Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21134,8 +18986,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "display_name": "Meta Llama 3.1 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21149,8 +18999,6 @@ "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "display_name": "Meta Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, @@ -21164,8 +19012,6 @@ "supports_tool_choice": true }, "hyperbolic/moonshotai/Kimi-K2-Instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", "input_cost_per_token": 2e-06, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, @@ -21179,8 +19025,6 @@ "supports_tool_choice": true }, "j2-light": { - "display_name": "J2 Light", - "model_vendor": "ai21", "input_cost_per_token": 3e-06, "litellm_provider": "ai21", "max_input_tokens": 8192, @@ -21190,8 +19034,6 @@ "output_cost_per_token": 3e-06 }, "j2-mid": { - "display_name": "J2 Mid", - "model_vendor": "ai21", "input_cost_per_token": 1e-05, "litellm_provider": "ai21", "max_input_tokens": 8192, @@ -21201,8 +19043,6 @@ "output_cost_per_token": 1e-05 }, "j2-ultra": { - "display_name": "J2 Ultra", - "model_vendor": "ai21", "input_cost_per_token": 1.5e-05, "litellm_provider": "ai21", "max_input_tokens": 8192, @@ -21212,8 +19052,6 @@ "output_cost_per_token": 1.5e-05 }, "jamba-1.5": { - "display_name": "Jamba 1.5", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21224,8 +19062,6 @@ "supports_tool_choice": true }, "jamba-1.5-large": { - "display_name": "Jamba 1.5 Large", - "model_vendor": "ai21", "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21236,8 +19072,6 @@ "supports_tool_choice": true }, "jamba-1.5-large@001": { - "display_name": "Jamba 1.5 Large @001", - "model_vendor": "ai21", "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21248,8 +19082,6 @@ "supports_tool_choice": true }, "jamba-1.5-mini": { - "display_name": "Jamba 1.5 Mini", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21260,8 +19092,6 @@ "supports_tool_choice": true }, "jamba-1.5-mini@001": { - "display_name": "Jamba 1.5 Mini @001", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21272,9 +19102,6 @@ "supports_tool_choice": true }, "jamba-large-1.6": { - "display_name": "Jamba Large 1.6", - "model_vendor": "ai21", - "model_version": "1.6", "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21285,9 +19112,6 @@ "supports_tool_choice": true }, "jamba-large-1.7": { - "display_name": "Jamba Large 1.7", - "model_vendor": "ai21", - "model_version": "1.7", "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21298,9 +19122,6 @@ "supports_tool_choice": true }, "jamba-mini-1.6": { - "display_name": "Jamba Mini 1.6", - "model_vendor": "ai21", - "model_version": "1.6", "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21311,9 +19132,6 @@ "supports_tool_choice": true }, "jamba-mini-1.7": { - "display_name": "Jamba Mini 1.7", - "model_vendor": "ai21", - "model_version": "1.7", "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, @@ -21324,8 +19142,6 @@ "supports_tool_choice": true }, "jina-reranker-v2-base-multilingual": { - "display_name": "Jina Reranker V2 Base Multilingual", - "model_vendor": "jina", "input_cost_per_token": 1.8e-08, "litellm_provider": "jina_ai", "max_document_chunks_per_query": 2048, @@ -21336,9 +19152,6 @@ "output_cost_per_token": 1.8e-08 }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 4.125e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, @@ -21369,9 +19182,6 @@ "tool_use_system_prompt_tokens": 346 }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, @@ -21394,8 +19204,6 @@ "tool_use_system_prompt_tokens": 346 }, "lambda_ai/deepseek-llama3.3-70b": { - "display_name": "DeepSeek Llama 3.3 70B", - "model_vendor": "deepseek", "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21410,9 +19218,6 @@ "supports_tool_choice": true }, "lambda_ai/deepseek-r1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21427,8 +19232,6 @@ "supports_tool_choice": true }, "lambda_ai/deepseek-r1-671b": { - "display_name": "DeepSeek R1 671B", - "model_vendor": "deepseek", "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21443,9 +19246,6 @@ "supports_tool_choice": true }, "lambda_ai/deepseek-v3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", - "model_version": "0324", "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21459,8 +19259,6 @@ "supports_tool_choice": true }, "lambda_ai/hermes3-405b": { - "display_name": "Hermes 3 405B", - "model_vendor": "nousresearch", "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21474,8 +19272,6 @@ "supports_tool_choice": true }, "lambda_ai/hermes3-70b": { - "display_name": "Hermes 3 70B", - "model_vendor": "nousresearch", "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21489,8 +19285,6 @@ "supports_tool_choice": true }, "lambda_ai/hermes3-8b": { - "display_name": "Hermes 3 8B", - "model_vendor": "nousresearch", "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21504,8 +19298,6 @@ "supports_tool_choice": true }, "lambda_ai/lfm-40b": { - "display_name": "LFM 40B", - "model_vendor": "lambda", "input_cost_per_token": 1e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21519,8 +19311,6 @@ "supports_tool_choice": true }, "lambda_ai/lfm-7b": { - "display_name": "LFM 7B", - "model_vendor": "lambda", "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21534,8 +19324,6 @@ "supports_tool_choice": true }, "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "display_name": "Llama 4 Maverick 17B 128E Instruct FP8", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21549,8 +19337,6 @@ "supports_tool_choice": true }, "lambda_ai/llama-4-scout-17b-16e-instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 16384, @@ -21564,8 +19350,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.1-405b-instruct-fp8": { - "display_name": "Llama 3.1 405B Instruct FP8", - "model_vendor": "meta", "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21579,8 +19363,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.1-70b-instruct-fp8": { - "display_name": "Llama 3.1 70B Instruct FP8", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21594,8 +19376,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.1-8b-instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21609,9 +19389,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "display_name": "Llama 3.1 Nemotron 70B Instruct FP8", - "model_vendor": "nvidia", - "model_version": "3.1-nemotron", "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21625,8 +19402,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.2-11b-vision-instruct": { - "display_name": "Llama 3.2 11B Vision Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21641,8 +19416,6 @@ "supports_vision": true }, "lambda_ai/llama3.2-3b-instruct": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21656,8 +19429,6 @@ "supports_tool_choice": true }, "lambda_ai/llama3.3-70b-instruct-fp8": { - "display_name": "Llama 3.3 70B Instruct FP8", - "model_vendor": "meta", "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21671,8 +19442,6 @@ "supports_tool_choice": true }, "lambda_ai/qwen25-coder-32b-instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21686,8 +19455,6 @@ "supports_tool_choice": true }, "lambda_ai/qwen3-32b-fp8": { - "display_name": "Qwen 3 32B FP8", - "model_vendor": "alibaba", "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, @@ -21702,8 +19469,6 @@ "supports_tool_choice": true }, "low/1024-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Low 1024x1024", - "model_vendor": "openai", "input_cost_per_image": 0.011, "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "openai", @@ -21714,8 +19479,6 @@ ] }, "low/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 Low 1024x1536", - "model_vendor": "openai", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", @@ -21726,8 +19489,6 @@ ] }, "low/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Low 1536x1024", - "model_vendor": "openai", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", @@ -21738,8 +19499,6 @@ ] }, "luminous-base": { - "display_name": "Luminous Base", - "model_vendor": "aleph_alpha", "input_cost_per_token": 3e-05, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21747,8 +19506,6 @@ "output_cost_per_token": 3.3e-05 }, "luminous-base-control": { - "display_name": "Luminous Base Control", - "model_vendor": "aleph_alpha", "input_cost_per_token": 3.75e-05, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21756,8 +19513,6 @@ "output_cost_per_token": 4.125e-05 }, "luminous-extended": { - "display_name": "Luminous Extended", - "model_vendor": "aleph_alpha", "input_cost_per_token": 4.5e-05, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21765,8 +19520,6 @@ "output_cost_per_token": 4.95e-05 }, "luminous-extended-control": { - "display_name": "Luminous Extended Control", - "model_vendor": "aleph_alpha", "input_cost_per_token": 5.625e-05, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21774,8 +19527,6 @@ "output_cost_per_token": 6.1875e-05 }, "luminous-supreme": { - "display_name": "Luminous Supreme", - "model_vendor": "aleph_alpha", "input_cost_per_token": 0.000175, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21783,8 +19534,6 @@ "output_cost_per_token": 0.0001925 }, "luminous-supreme-control": { - "display_name": "Luminous Supreme Control", - "model_vendor": "aleph_alpha", "input_cost_per_token": 0.00021875, "litellm_provider": "aleph_alpha", "max_tokens": 2048, @@ -21792,9 +19541,6 @@ "output_cost_per_token": 0.000240625 }, "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "display_name": "Stable Diffusion XL V0 50 Steps", - "model_vendor": "stability", - "model_version": "xl-v0", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -21802,9 +19548,6 @@ "output_cost_per_image": 0.036 }, "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "display_name": "Stable Diffusion XL V0 Max Steps", - "model_vendor": "stability", - "model_version": "xl-v0", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -21812,8 +19555,6 @@ "output_cost_per_image": 0.072 }, "medium/1024-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Medium 1024x1024", - "model_vendor": "openai", "input_cost_per_image": 0.042, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -21824,8 +19565,6 @@ ] }, "medium/1024-x-1536/gpt-image-1": { - "display_name": "GPT Image 1 Medium 1024x1536", - "model_vendor": "openai", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -21836,8 +19575,6 @@ ] }, "medium/1536-x-1024/gpt-image-1": { - "display_name": "GPT Image 1 Medium 1536x1024", - "model_vendor": "openai", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -21848,9 +19585,6 @@ ] }, "low/1024-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low 1024x1024", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.005, "litellm_provider": "openai", "mode": "image_generation", @@ -21859,9 +19593,6 @@ ] }, "low/1024-x-1536/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low 1024x1536", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", @@ -21870,9 +19601,6 @@ ] }, "low/1536-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Low 1536x1024", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", @@ -21881,9 +19609,6 @@ ] }, "medium/1024-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium 1024x1024", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.011, "litellm_provider": "openai", "mode": "image_generation", @@ -21892,9 +19617,6 @@ ] }, "medium/1024-x-1536/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium 1024x1536", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", @@ -21903,9 +19625,6 @@ ] }, "medium/1536-x-1024/gpt-image-1-mini": { - "display_name": "GPT Image 1 Mini Medium 1536x1024", - "model_vendor": "openai", - "model_version": "1-mini", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", @@ -21914,8 +19633,6 @@ ] }, "medlm-large": { - "display_name": "MedLM Large", - "model_vendor": "google", "input_cost_per_character": 5e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 8192, @@ -21927,8 +19644,6 @@ "supports_tool_choice": true }, "medlm-medium": { - "display_name": "MedLM Medium", - "model_vendor": "google", "input_cost_per_character": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, @@ -21940,8 +19655,6 @@ "supports_tool_choice": true }, "meta.llama2-13b-chat-v1": { - "display_name": "Llama 2 13B Chat", - "model_vendor": "meta", "input_cost_per_token": 7.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 4096, @@ -21951,8 +19664,6 @@ "output_cost_per_token": 1e-06 }, "meta.llama2-70b-chat-v1": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "input_cost_per_token": 1.95e-06, "litellm_provider": "bedrock", "max_input_tokens": 4096, @@ -21962,8 +19673,6 @@ "output_cost_per_token": 2.56e-06 }, "meta.llama3-1-405b-instruct-v1:0": { - "display_name": "Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5.32e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -21975,8 +19684,6 @@ "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { - "display_name": "Llama 3.1 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 9.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -21988,8 +19695,6 @@ "supports_tool_choice": false }, "meta.llama3-1-8b-instruct-v1:0": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22001,8 +19706,6 @@ "supports_tool_choice": false }, "meta.llama3-2-11b-instruct-v1:0": { - "display_name": "Llama 3.2 11B Instruct", - "model_vendor": "meta", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22015,8 +19718,6 @@ "supports_vision": true }, "meta.llama3-2-1b-instruct-v1:0": { - "display_name": "Llama 3.2 1B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22028,8 +19729,6 @@ "supports_tool_choice": false }, "meta.llama3-2-3b-instruct-v1:0": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22041,8 +19740,6 @@ "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { - "display_name": "Llama 3.2 90B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22055,8 +19752,6 @@ "supports_vision": true }, "meta.llama3-3-70b-instruct-v1:0": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22068,8 +19763,6 @@ "supports_tool_choice": false }, "meta.llama3-70b-instruct-v1:0": { - "display_name": "Llama 3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, @@ -22079,8 +19772,6 @@ "output_cost_per_token": 3.5e-06 }, "meta.llama3-8b-instruct-v1:0": { - "display_name": "Llama 3 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, @@ -22090,8 +19781,6 @@ "output_cost_per_token": 6e-07 }, "meta.llama4-maverick-17b-instruct-v1:0": { - "display_name": "Llama 4 Maverick 17B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", @@ -22113,8 +19802,6 @@ "supports_tool_choice": false }, "meta.llama4-scout-17b-instruct-v1:0": { - "display_name": "Llama 4 Scout 17B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", @@ -22136,8 +19823,6 @@ "supports_tool_choice": false }, "meta_llama/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, @@ -22154,8 +19839,6 @@ "supports_tool_choice": true }, "meta_llama/Llama-3.3-8B-Instruct": { - "display_name": "Llama 3.3 8B Instruct", - "model_vendor": "meta", "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, @@ -22172,8 +19855,6 @@ "supports_tool_choice": true }, "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "display_name": "Llama 4 Maverick 17B 128E Instruct FP8", - "model_vendor": "meta", "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, @@ -22191,8 +19872,6 @@ "supports_tool_choice": true }, "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { - "display_name": "Llama 4 Scout 17B 16E Instruct FP8", - "model_vendor": "meta", "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, @@ -22210,8 +19889,6 @@ "supports_tool_choice": true }, "minimax.minimax-m2": { - "display_name": "Minimax M2", - "model_vendor": "minimax", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22221,9 +19898,81 @@ "output_cost_per_token": 1.2e-06, "supports_system_messages": true }, + "minimax/speech-02-hd": { + "input_cost_per_character": 0.0001, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-02-turbo": { + "input_cost_per_character": 0.00006, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-2.6-hd": { + "input_cost_per_character": 0.0001, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/speech-2.6-turbo": { + "input_cost_per_character": 0.00006, + "litellm_provider": "minimax", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "minimax/MiniMax-M2.1": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2.1-lightning": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "max_input_tokens": 200000, + "max_output_tokens": 8192 + }, "mistral.magistral-small-2509": { - "display_name": "Magistral Small 2509", - "model_vendor": "mistral", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22236,8 +19985,6 @@ "supports_system_messages": true }, "mistral.ministral-3-14b-instruct": { - "display_name": "Ministral 3 14B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22249,8 +19996,6 @@ "supports_system_messages": true }, "mistral.ministral-3-3b-instruct": { - "display_name": "Ministral 3 3B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22262,8 +20007,6 @@ "supports_system_messages": true }, "mistral.ministral-3-8b-instruct": { - "display_name": "Ministral 3 8B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22275,9 +20018,6 @@ "supports_system_messages": true }, "mistral.mistral-7b-instruct-v0:2": { - "display_name": "Mistral 7B Instruct V0.2", - "model_vendor": "mistralai", - "model_version": "0.2", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, @@ -22288,9 +20028,6 @@ "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { - "display_name": "Mistral Large 2402", - "model_vendor": "mistralai", - "model_version": "2402", "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, @@ -22301,9 +20038,6 @@ "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { - "display_name": "Mistral Large 2407", - "model_vendor": "mistralai", - "model_version": "2407", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22315,8 +20049,6 @@ "supports_tool_choice": true }, "mistral.mistral-large-3-675b-instruct": { - "display_name": "Mistral Large 3 675B Instruct", - "model_vendor": "mistral", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22328,9 +20060,6 @@ "supports_system_messages": true }, "mistral.mistral-small-2402-v1:0": { - "display_name": "Mistral Small 2402", - "model_vendor": "mistralai", - "model_version": "2402", "input_cost_per_token": 1e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, @@ -22341,8 +20070,6 @@ "supports_function_calling": true }, "mistral.mixtral-8x7b-instruct-v0:1": { - "display_name": "Mixtral 8x7B Instruct V0.1", - "model_vendor": "mistralai", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, @@ -22353,8 +20080,6 @@ "supports_tool_choice": true }, "mistral.voxtral-mini-3b-2507": { - "display_name": "Voxtral Mini 3B 2507", - "model_vendor": "mistral", "input_cost_per_token": 4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22366,8 +20091,6 @@ "supports_system_messages": true }, "mistral.voxtral-small-24b-2507": { - "display_name": "Voxtral Small 24B 2507", - "model_vendor": "mistral", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22379,9 +20102,6 @@ "supports_system_messages": true }, "mistral/codestral-2405": { - "display_name": "Codestral 2405", - "model_vendor": "mistralai", - "model_version": "2405", "input_cost_per_token": 1e-06, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22394,8 +20114,6 @@ "supports_tool_choice": true }, "mistral/codestral-2508": { - "display_name": "Mistral Codestral 2508", - "model_vendor": "mistral", "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22410,8 +20128,6 @@ "supports_tool_choice": true }, "mistral/codestral-latest": { - "display_name": "Codestral Latest", - "model_vendor": "mistralai", "input_cost_per_token": 1e-06, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22424,8 +20140,6 @@ "supports_tool_choice": true }, "mistral/codestral-mamba-latest": { - "display_name": "Codestral Mamba Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22438,9 +20152,6 @@ "supports_tool_choice": true }, "mistral/devstral-medium-2507": { - "display_name": "Devstral Medium 2507", - "model_vendor": "mistralai", - "model_version": "2507", "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22455,9 +20166,6 @@ "supports_tool_choice": true }, "mistral/devstral-small-2505": { - "display_name": "Devstral Small 2505", - "model_vendor": "mistralai", - "model_version": "2505", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22472,9 +20180,6 @@ "supports_tool_choice": true }, "mistral/devstral-small-2507": { - "display_name": "Devstral Small 2507", - "model_vendor": "mistralai", - "model_version": "2507", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22489,8 +20194,6 @@ "supports_tool_choice": true }, "mistral/labs-devstral-small-2512": { - "display_name": "Mistral Labs Devstral Small 2512", - "model_vendor": "mistral", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22505,8 +20208,6 @@ "supports_tool_choice": true }, "mistral/devstral-2512": { - "display_name": "Mistral Devstral 2512", - "model_vendor": "mistral", "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22521,9 +20222,6 @@ "supports_tool_choice": true }, "mistral/magistral-medium-2506": { - "display_name": "Magistral Medium 2506", - "model_vendor": "mistralai", - "model_version": "2506", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 40000, @@ -22539,9 +20237,6 @@ "supports_tool_choice": true }, "mistral/magistral-medium-2509": { - "display_name": "Magistral Medium 2509", - "model_vendor": "mistralai", - "model_version": "2509", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 40000, @@ -22557,11 +20252,9 @@ "supports_tool_choice": true }, "mistral/mistral-ocr-latest": { - "display_name": "Mistral OCR Latest", - "model_vendor": "mistralai", "litellm_provider": "mistral", - "ocr_cost_per_page": 0.001, - "annotation_cost_per_page": 0.003, + "ocr_cost_per_page": 1e-3, + "annotation_cost_per_page": 3e-3, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" @@ -22569,12 +20262,9 @@ "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-2505-completion": { - "display_name": "Mistral OCR 2505 Completion", - "model_vendor": "mistralai", - "model_version": "2505", "litellm_provider": "mistral", - "ocr_cost_per_page": 0.001, - "annotation_cost_per_page": 0.003, + "ocr_cost_per_page": 1e-3, + "annotation_cost_per_page": 3e-3, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" @@ -22582,8 +20272,6 @@ "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/magistral-medium-latest": { - "display_name": "Magistral Medium Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 40000, @@ -22599,9 +20287,6 @@ "supports_tool_choice": true }, "mistral/magistral-small-2506": { - "display_name": "Magistral Small 2506", - "model_vendor": "mistralai", - "model_version": "2506", "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 40000, @@ -22617,8 +20302,6 @@ "supports_tool_choice": true }, "mistral/magistral-small-latest": { - "display_name": "Magistral Small Latest", - "model_vendor": "mistralai", "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 40000, @@ -22634,8 +20317,6 @@ "supports_tool_choice": true }, "mistral/mistral-embed": { - "display_name": "Mistral Embed", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, @@ -22643,28 +20324,20 @@ "mode": "embedding" }, "mistral/codestral-embed": { - "display_name": "Codestral Embed", - "model_vendor": "mistralai", - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 0.15e-06, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed-2505": { - "display_name": "Codestral Embed 2505", - "model_vendor": "mistralai", - "model_version": "2505", - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 0.15e-06, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" }, "mistral/mistral-large-2402": { - "display_name": "Mistral Large 2402", - "model_vendor": "mistralai", - "model_version": "2402", "input_cost_per_token": 4e-06, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22678,9 +20351,6 @@ "supports_tool_choice": true }, "mistral/mistral-large-2407": { - "display_name": "Mistral Large 2407", - "model_vendor": "mistralai", - "model_version": "2407", "input_cost_per_token": 3e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22694,9 +20364,6 @@ "supports_tool_choice": true }, "mistral/mistral-large-2411": { - "display_name": "Mistral Large 2411", - "model_vendor": "mistralai", - "model_version": "2411", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22710,8 +20377,6 @@ "supports_tool_choice": true }, "mistral/mistral-large-latest": { - "display_name": "Mistral Large Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22725,8 +20390,6 @@ "supports_tool_choice": true }, "mistral/mistral-large-3": { - "display_name": "Mistral Mistral Large 3", - "model_vendor": "mistral", "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22742,8 +20405,6 @@ "supports_vision": true }, "mistral/mistral-medium": { - "display_name": "Mistral Medium", - "model_vendor": "mistralai", "input_cost_per_token": 2.7e-06, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22756,9 +20417,6 @@ "supports_tool_choice": true }, "mistral/mistral-medium-2312": { - "display_name": "Mistral Medium 2312", - "model_vendor": "mistralai", - "model_version": "2312", "input_cost_per_token": 2.7e-06, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22771,9 +20429,6 @@ "supports_tool_choice": true }, "mistral/mistral-medium-2505": { - "display_name": "Mistral Medium 2505", - "model_vendor": "mistralai", - "model_version": "2505", "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, @@ -22787,8 +20442,6 @@ "supports_tool_choice": true }, "mistral/mistral-medium-latest": { - "display_name": "Mistral Medium Latest", - "model_vendor": "mistralai", "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, @@ -22802,8 +20455,6 @@ "supports_tool_choice": true }, "mistral/mistral-small": { - "display_name": "Mistral Small", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22817,8 +20468,6 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "display_name": "Mistral Small Latest", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22832,8 +20481,6 @@ "supports_tool_choice": true }, "mistral/mistral-tiny": { - "display_name": "Mistral Tiny", - "model_vendor": "mistralai", "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22846,8 +20493,6 @@ "supports_tool_choice": true }, "mistral/open-codestral-mamba": { - "display_name": "Open Codestral Mamba", - "model_vendor": "mistralai", "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -22860,8 +20505,6 @@ "supports_tool_choice": true }, "mistral/open-mistral-7b": { - "display_name": "Open Mistral 7B", - "model_vendor": "mistralai", "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22874,8 +20517,6 @@ "supports_tool_choice": true }, "mistral/open-mistral-nemo": { - "display_name": "Open Mistral Nemo", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22889,9 +20530,6 @@ "supports_tool_choice": true }, "mistral/open-mistral-nemo-2407": { - "display_name": "Open Mistral Nemo 2407", - "model_vendor": "mistralai", - "model_version": "2407", "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22905,8 +20543,6 @@ "supports_tool_choice": true }, "mistral/open-mixtral-8x22b": { - "display_name": "Open Mixtral 8x22B", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 65336, @@ -22920,8 +20556,6 @@ "supports_tool_choice": true }, "mistral/open-mixtral-8x7b": { - "display_name": "Open Mixtral 8x7B", - "model_vendor": "mistralai", "input_cost_per_token": 7e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -22935,9 +20569,6 @@ "supports_tool_choice": true }, "mistral/pixtral-12b-2409": { - "display_name": "Pixtral 12B 2409", - "model_vendor": "mistralai", - "model_version": "2409", "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22952,9 +20583,6 @@ "supports_vision": true }, "mistral/pixtral-large-2411": { - "display_name": "Pixtral Large 2411", - "model_vendor": "mistralai", - "model_version": "2411", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22969,8 +20597,6 @@ "supports_vision": true }, "mistral/pixtral-large-latest": { - "display_name": "Pixtral Large Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -22985,8 +20611,6 @@ "supports_vision": true }, "moonshot.kimi-k2-thinking": { - "display_name": "Kimi K2 Thinking", - "model_vendor": "moonshot", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -22998,9 +20622,6 @@ "supports_system_messages": true }, "moonshot/kimi-k2-0711-preview": { - "display_name": "Kimi K2 0711 Preview", - "model_vendor": "moonshot", - "model_version": "k2-0711", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", @@ -23015,9 +20636,6 @@ "supports_web_search": true }, "moonshot/kimi-k2-0905-preview": { - "display_name": "Kimi K2 0905 Preview", - "model_vendor": "moonshot", - "model_version": "0905-preview", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", @@ -23032,9 +20650,6 @@ "supports_web_search": true }, "moonshot/kimi-k2-turbo-preview": { - "display_name": "Kimi K2 Turbo Preview", - "model_vendor": "moonshot", - "model_version": "turbo-preview", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.15e-06, "litellm_provider": "moonshot", @@ -23049,8 +20664,6 @@ "supports_web_search": true }, "moonshot/kimi-latest": { - "display_name": "Kimi Latest", - "model_vendor": "moonshot", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -23065,8 +20678,6 @@ "supports_vision": true }, "moonshot/kimi-latest-128k": { - "display_name": "Kimi Latest 128K", - "model_vendor": "moonshot", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -23081,8 +20692,6 @@ "supports_vision": true }, "moonshot/kimi-latest-32k": { - "display_name": "Kimi Latest 32K", - "model_vendor": "moonshot", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", @@ -23097,8 +20706,6 @@ "supports_vision": true }, "moonshot/kimi-latest-8k": { - "display_name": "Kimi Latest 8K", - "model_vendor": "moonshot", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", @@ -23113,8 +20720,6 @@ "supports_vision": true }, "moonshot/kimi-thinking-preview": { - "display_name": "Kimi Thinking Preview", - "model_vendor": "moonshot", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", @@ -23127,41 +20732,34 @@ "supports_vision": true }, "moonshot/kimi-k2-thinking": { - "display_name": "Kimi K2 Thinking", - "model_vendor": "moonshot", - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 2.5e-6, "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-k2-thinking-turbo": { - "display_name": "Kimi K2 Thinking Turbo", - "model_vendor": "moonshot", - "model_version": "thinking-turbo", - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 1.15e-6, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8e-06, + "output_cost_per_token": 8e-6, "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/moonshot-v1-128k": { - "display_name": "Moonshot V1 128K", - "model_vendor": "moonshot", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23174,9 +20772,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-0430": { - "display_name": "Moonshot V1 128K 0430", - "model_vendor": "moonshot", - "model_version": "0430", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23189,8 +20784,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-vision-preview": { - "display_name": "Moonshot V1 128K Vision Preview", - "model_vendor": "moonshot", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23204,8 +20797,6 @@ "supports_vision": true }, "moonshot/moonshot-v1-32k": { - "display_name": "Moonshot V1 32K", - "model_vendor": "moonshot", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -23218,9 +20809,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-0430": { - "display_name": "Moonshot V1 32K 0430", - "model_vendor": "moonshot", - "model_version": "0430", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -23233,8 +20821,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-vision-preview": { - "display_name": "Moonshot V1 32K Vision Preview", - "model_vendor": "moonshot", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -23248,8 +20834,6 @@ "supports_vision": true }, "moonshot/moonshot-v1-8k": { - "display_name": "Moonshot V1 8K", - "model_vendor": "moonshot", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -23262,9 +20846,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-0430": { - "display_name": "Moonshot V1 8K 0430", - "model_vendor": "moonshot", - "model_version": "0430", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -23277,8 +20858,6 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-vision-preview": { - "display_name": "Moonshot V1 8K Vision Preview", - "model_vendor": "moonshot", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -23292,8 +20871,6 @@ "supports_vision": true }, "moonshot/moonshot-v1-auto": { - "display_name": "Moonshot V1 Auto", - "model_vendor": "moonshot", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23306,8 +20883,6 @@ "supports_tool_choice": true }, "morph/morph-v3-fast": { - "display_name": "Morph V3 Fast", - "model_vendor": "morph", "input_cost_per_token": 8e-07, "litellm_provider": "morph", "max_input_tokens": 16000, @@ -23322,8 +20897,6 @@ "supports_vision": false }, "morph/morph-v3-large": { - "display_name": "Morph V3 Large", - "model_vendor": "morph", "input_cost_per_token": 9e-07, "litellm_provider": "morph", "max_input_tokens": 16000, @@ -23338,8 +20911,6 @@ "supports_vision": false }, "multimodalembedding": { - "display_name": "Multimodal Embedding", - "model_vendor": "google", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -23363,9 +20934,6 @@ ] }, "multimodalembedding@001": { - "display_name": "Multimodal Embedding 001", - "model_vendor": "google", - "model_version": "001", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -23389,8 +20957,6 @@ ] }, "nscale/Qwen/QwQ-32B": { - "display_name": "QwQ 32B", - "model_vendor": "alibaba", "input_cost_per_token": 1.8e-07, "litellm_provider": "nscale", "mode": "chat", @@ -23398,8 +20964,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 6e-08, "litellm_provider": "nscale", "mode": "chat", @@ -23407,8 +20971,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { - "display_name": "Qwen 2.5 Coder 3B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1e-08, "litellm_provider": "nscale", "mode": "chat", @@ -23416,8 +20978,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { - "display_name": "Qwen 2.5 Coder 7B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1e-08, "litellm_provider": "nscale", "mode": "chat", @@ -23425,8 +20985,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/black-forest-labs/FLUX.1-schnell": { - "display_name": "FLUX.1 Schnell", - "model_vendor": "black_forest_labs", "input_cost_per_pixel": 1.3e-09, "litellm_provider": "nscale", "mode": "image_generation", @@ -23437,8 +20995,6 @@ ] }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "input_cost_per_token": 3.75e-07, "litellm_provider": "nscale", "metadata": { @@ -23449,8 +21005,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { - "display_name": "DeepSeek R1 Distill Llama 8B", - "model_vendor": "deepseek", "input_cost_per_token": 2.5e-08, "litellm_provider": "nscale", "metadata": { @@ -23461,8 +21015,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "display_name": "DeepSeek R1 Distill Qwen 1.5B", - "model_vendor": "deepseek", "input_cost_per_token": 9e-08, "litellm_provider": "nscale", "metadata": { @@ -23473,8 +21025,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "display_name": "DeepSeek R1 Distill Qwen 14B", - "model_vendor": "deepseek", "input_cost_per_token": 7e-08, "litellm_provider": "nscale", "metadata": { @@ -23485,8 +21035,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "display_name": "DeepSeek R1 Distill Qwen 32B", - "model_vendor": "deepseek", "input_cost_per_token": 1.5e-07, "litellm_provider": "nscale", "metadata": { @@ -23497,8 +21045,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { - "display_name": "DeepSeek R1 Distill Qwen 7B", - "model_vendor": "deepseek", "input_cost_per_token": 2e-07, "litellm_provider": "nscale", "metadata": { @@ -23509,8 +21055,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-3.1-8B-Instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 3e-08, "litellm_provider": "nscale", "metadata": { @@ -23521,8 +21065,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "nscale", "metadata": { @@ -23533,8 +21075,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "input_cost_per_token": 9e-08, "litellm_provider": "nscale", "mode": "chat", @@ -23542,8 +21082,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { - "display_name": "Mixtral 8x22B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 6e-07, "litellm_provider": "nscale", "metadata": { @@ -23554,9 +21092,6 @@ "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/stabilityai/stable-diffusion-xl-base-1.0": { - "display_name": "Stable Diffusion XL Base 1.0", - "model_vendor": "stability", - "model_version": "xl-1.0", "input_cost_per_pixel": 3e-09, "litellm_provider": "nscale", "mode": "image_generation", @@ -23567,8 +21102,6 @@ ] }, "nvidia.nemotron-nano-12b-v2": { - "display_name": "Nemotron Nano 12B V2", - "model_vendor": "nvidia", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -23580,8 +21113,6 @@ "supports_vision": true }, "nvidia.nemotron-nano-9b-v2": { - "display_name": "Nemotron Nano 9B V2", - "model_vendor": "nvidia", "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -23592,8 +21123,6 @@ "supports_system_messages": true }, "o1": { - "display_name": "o1", - "model_vendor": "openai", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openai", @@ -23613,9 +21142,6 @@ "supports_vision": true }, "o1-2024-12-17": { - "display_name": "o1", - "model_vendor": "openai", - "model_version": "2024-12-17", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openai", @@ -23635,8 +21161,6 @@ "supports_vision": true }, "o1-mini": { - "display_name": "o1 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "openai", @@ -23650,9 +21174,6 @@ "supports_vision": true }, "o1-mini-2024-09-12": { - "display_name": "o1 Mini", - "model_vendor": "openai", - "model_version": "2024-09-12", "deprecation_date": "2025-10-27", "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 3e-06, @@ -23668,8 +21189,6 @@ "supports_vision": true }, "o1-preview": { - "display_name": "o1 Preview", - "model_vendor": "openai", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openai", @@ -23684,9 +21203,6 @@ "supports_vision": true }, "o1-preview-2024-09-12": { - "display_name": "o1 Preview", - "model_vendor": "openai", - "model_version": "2024-09-12", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openai", @@ -23701,8 +21217,6 @@ "supports_vision": true }, "o1-pro": { - "display_name": "o1 Pro", - "model_vendor": "openai", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", @@ -23735,9 +21249,6 @@ "supports_vision": true }, "o1-pro-2025-03-19": { - "display_name": "o1 Pro", - "model_vendor": "openai", - "model_version": "2025-03-19", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", @@ -23770,8 +21281,6 @@ "supports_vision": true }, "o3": { - "display_name": "o3", - "model_vendor": "openai", "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, @@ -23810,9 +21319,6 @@ "supports_vision": true }, "o3-2025-04-16": { - "display_name": "o3", - "model_vendor": "openai", - "model_version": "2025-04-16", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", @@ -23845,8 +21351,6 @@ "supports_vision": true }, "o3-deep-research": { - "display_name": "o3 Deep Research", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, @@ -23880,9 +21384,6 @@ "supports_vision": true }, "o3-deep-research-2025-06-26": { - "display_name": "o3 Deep Research", - "model_vendor": "openai", - "model_version": "2025-06-26", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, @@ -23916,8 +21417,6 @@ "supports_vision": true }, "o3-mini": { - "display_name": "o3 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "openai", @@ -23935,9 +21434,6 @@ "supports_vision": false }, "o3-mini-2025-01-31": { - "display_name": "o3 Mini", - "model_vendor": "openai", - "model_version": "2025-01-31", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "openai", @@ -23955,8 +21451,6 @@ "supports_vision": false }, "o3-pro": { - "display_name": "o3 Pro", - "model_vendor": "openai", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", @@ -23987,9 +21481,6 @@ "supports_vision": true }, "o3-pro-2025-06-10": { - "display_name": "o3 Pro", - "model_vendor": "openai", - "model_version": "2025-06-10", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", @@ -24020,8 +21511,6 @@ "supports_vision": true }, "o4-mini": { - "display_name": "o4 Mini", - "model_vendor": "openai", "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, @@ -24047,9 +21536,6 @@ "supports_vision": true }, "o4-mini-2025-04-16": { - "display_name": "o4 Mini", - "model_vendor": "openai", - "model_version": "2025-04-16", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "openai", @@ -24069,8 +21555,6 @@ "supports_vision": true }, "o4-mini-deep-research": { - "display_name": "o4 Mini Deep Research", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -24104,9 +21588,6 @@ "supports_vision": true }, "o4-mini-deep-research-2025-06-26": { - "display_name": "o4 Mini Deep Research", - "model_vendor": "openai", - "model_version": "2025-06-26", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -24140,8 +21621,6 @@ "supports_vision": true }, "oci/meta.llama-3.1-405b-instruct": { - "display_name": "Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1.068e-05, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24154,8 +21633,6 @@ "supports_response_schema": false }, "oci/meta.llama-3.2-90b-vision-instruct": { - "display_name": "Llama 3.2 90B Vision Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-06, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24168,8 +21645,6 @@ "supports_response_schema": false }, "oci/meta.llama-3.3-70b-instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24182,8 +21657,6 @@ "supports_response_schema": false }, "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { - "display_name": "Llama 4 Maverick 17B 128E Instruct FP8", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 512000, @@ -24196,8 +21669,6 @@ "supports_response_schema": false }, "oci/meta.llama-4-scout-17b-16e-instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 192000, @@ -24210,8 +21681,6 @@ "supports_response_schema": false }, "oci/xai.grok-3": { - "display_name": "Grok 3", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 131072, @@ -24224,8 +21693,6 @@ "supports_response_schema": false }, "oci/xai.grok-3-fast": { - "display_name": "Grok 3 Fast", - "model_vendor": "xai", "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, @@ -24238,8 +21705,6 @@ "supports_response_schema": false }, "oci/xai.grok-3-mini": { - "display_name": "Grok 3 Mini", - "model_vendor": "xai", "input_cost_per_token": 3e-07, "litellm_provider": "oci", "max_input_tokens": 131072, @@ -24252,8 +21717,6 @@ "supports_response_schema": false }, "oci/xai.grok-3-mini-fast": { - "display_name": "Grok 3 Mini Fast", - "model_vendor": "xai", "input_cost_per_token": 6e-07, "litellm_provider": "oci", "max_input_tokens": 131072, @@ -24266,8 +21729,6 @@ "supports_response_schema": false }, "oci/xai.grok-4": { - "display_name": "Grok 4", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24280,8 +21741,6 @@ "supports_response_schema": false }, "oci/cohere.command-latest": { - "display_name": "Command Latest", - "model_vendor": "cohere", "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24294,9 +21753,6 @@ "supports_response_schema": false }, "oci/cohere.command-a-03-2025": { - "display_name": "Command A 03-2025", - "model_vendor": "cohere", - "model_version": "03-2025", "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 256000, @@ -24309,8 +21765,6 @@ "supports_response_schema": false }, "oci/cohere.command-plus-latest": { - "display_name": "Command Plus Latest", - "model_vendor": "cohere", "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, @@ -24323,8 +21777,6 @@ "supports_response_schema": false }, "ollama/codegeex4": { - "display_name": "CodeGeeX4", - "model_vendor": "zhipu", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24335,8 +21787,6 @@ "supports_function_calling": false }, "ollama/codegemma": { - "display_name": "CodeGemma", - "model_vendor": "google", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24346,8 +21796,6 @@ "output_cost_per_token": 0.0 }, "ollama/codellama": { - "display_name": "Code Llama", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24357,8 +21805,6 @@ "output_cost_per_token": 0.0 }, "ollama/deepseek-coder-v2-base": { - "display_name": "DeepSeek Coder V2 Base", - "model_vendor": "deepseek", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24369,8 +21815,6 @@ "supports_function_calling": true }, "ollama/deepseek-coder-v2-instruct": { - "display_name": "DeepSeek Coder V2 Instruct", - "model_vendor": "deepseek", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24381,8 +21825,6 @@ "supports_function_calling": true }, "ollama/deepseek-coder-v2-lite-base": { - "display_name": "DeepSeek Coder V2 Lite Base", - "model_vendor": "deepseek", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24393,8 +21835,6 @@ "supports_function_calling": true }, "ollama/deepseek-coder-v2-lite-instruct": { - "display_name": "DeepSeek Coder V2 Lite Instruct", - "model_vendor": "deepseek", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24404,9 +21844,7 @@ "output_cost_per_token": 0.0, "supports_function_calling": true }, - "ollama/deepseek-v3.1:671b-cloud": { - "display_name": "DeepSeek V3.1 671B Cloud", - "model_vendor": "deepseek", + "ollama/deepseek-v3.1:671b-cloud" : { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 163840, @@ -24416,9 +21854,7 @@ "output_cost_per_token": 0.0, "supports_function_calling": true }, - "ollama/gpt-oss:120b-cloud": { - "display_name": "GPT-OSS 120B Cloud", - "model_vendor": "openai", + "ollama/gpt-oss:120b-cloud" : { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 131072, @@ -24428,9 +21864,7 @@ "output_cost_per_token": 0.0, "supports_function_calling": true }, - "ollama/gpt-oss:20b-cloud": { - "display_name": "GPT-OSS 20B Cloud", - "model_vendor": "openai", + "ollama/gpt-oss:20b-cloud" : { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 131072, @@ -24441,8 +21875,6 @@ "supports_function_calling": true }, "ollama/internlm2_5-20b-chat": { - "display_name": "InternLM 2.5 20B Chat", - "model_vendor": "shanghai_ai_lab", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24453,8 +21885,6 @@ "supports_function_calling": true }, "ollama/llama2": { - "display_name": "Llama 2", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24464,8 +21894,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama2-uncensored": { - "display_name": "Llama 2 Uncensored", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24475,8 +21903,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama2:13b": { - "display_name": "Llama 2 13B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24486,8 +21912,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama2:70b": { - "display_name": "Llama 2 70B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24497,8 +21921,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama2:7b": { - "display_name": "Llama 2 7B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24508,8 +21930,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama3": { - "display_name": "Llama 3", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24519,8 +21939,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama3.1": { - "display_name": "Llama 3.1", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24531,8 +21949,6 @@ "supports_function_calling": true }, "ollama/llama3:70b": { - "display_name": "Llama 3 70B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24542,8 +21958,6 @@ "output_cost_per_token": 0.0 }, "ollama/llama3:8b": { - "display_name": "Llama 3 8B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24553,8 +21967,6 @@ "output_cost_per_token": 0.0 }, "ollama/mistral": { - "display_name": "Mistral", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24565,8 +21977,6 @@ "supports_function_calling": true }, "ollama/mistral-7B-Instruct-v0.1": { - "display_name": "Mistral 7B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, @@ -24577,9 +21987,6 @@ "supports_function_calling": true }, "ollama/mistral-7B-Instruct-v0.2": { - "display_name": "Mistral 7B Instruct v0.2", - "model_vendor": "mistralai", - "model_version": "0.2", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24590,9 +21997,6 @@ "supports_function_calling": true }, "ollama/mistral-large-instruct-2407": { - "display_name": "Mistral Large Instruct 2407", - "model_vendor": "mistralai", - "model_version": "2407", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 65536, @@ -24603,8 +22007,6 @@ "supports_function_calling": true }, "ollama/mixtral-8x22B-Instruct-v0.1": { - "display_name": "Mixtral 8x22B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 65536, @@ -24615,8 +22017,6 @@ "supports_function_calling": true }, "ollama/mixtral-8x7B-Instruct-v0.1": { - "display_name": "Mixtral 8x7B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, @@ -24627,8 +22027,6 @@ "supports_function_calling": true }, "ollama/orca-mini": { - "display_name": "Orca Mini", - "model_vendor": "microsoft", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, @@ -24638,8 +22036,6 @@ "output_cost_per_token": 0.0 }, "ollama/qwen3-coder:480b-cloud": { - "display_name": "Qwen 3 Coder 480B Cloud", - "model_vendor": "alibaba", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 262144, @@ -24650,8 +22046,6 @@ "supports_function_calling": true }, "ollama/vicuna": { - "display_name": "Vicuna", - "model_vendor": "lmsys", "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 2048, @@ -24661,9 +22055,6 @@ "output_cost_per_token": 0.0 }, "omni-moderation-2024-09-26": { - "display_name": "Omni Moderation", - "model_vendor": "openai", - "model_version": "2024-09-26", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -24673,8 +22064,6 @@ "output_cost_per_token": 0.0 }, "omni-moderation-latest": { - "display_name": "Omni Moderation Latest", - "model_vendor": "openai", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -24684,8 +22073,6 @@ "output_cost_per_token": 0.0 }, "omni-moderation-latest-intents": { - "display_name": "Omni Moderation Latest Intents", - "model_vendor": "openai", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -24695,8 +22082,6 @@ "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -24710,8 +22095,6 @@ "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -24725,8 +22108,6 @@ "supports_tool_choice": true }, "openai.gpt-oss-safeguard-120b": { - "display_name": "GPT Oss Safeguard 120B", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -24737,8 +22118,6 @@ "supports_system_messages": true }, "openai.gpt-oss-safeguard-20b": { - "display_name": "GPT Oss Safeguard 20B", - "model_vendor": "openai", "input_cost_per_token": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -24749,8 +22128,6 @@ "supports_system_messages": true }, "openrouter/anthropic/claude-2": { - "display_name": "Claude 2", - "model_vendor": "anthropic", "input_cost_per_token": 1.102e-05, "litellm_provider": "openrouter", "max_output_tokens": 8191, @@ -24760,8 +22137,6 @@ "supports_tool_choice": true }, "openrouter/anthropic/claude-3-5-haiku": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_tokens": 200000, @@ -24771,9 +22146,6 @@ "supports_tool_choice": true }, "openrouter/anthropic/claude-3-5-haiku-20241022": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", - "model_version": "20241022", "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -24786,8 +22158,6 @@ "tool_use_system_prompt_tokens": 264 }, "openrouter/anthropic/claude-3-haiku": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", "input_cost_per_image": 0.0004, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", @@ -24799,9 +22169,6 @@ "supports_vision": true }, "openrouter/anthropic/claude-3-haiku-20240307": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", - "model_version": "20240307", "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -24815,8 +22182,6 @@ "tool_use_system_prompt_tokens": 264 }, "openrouter/anthropic/claude-3-opus": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -24830,8 +22195,6 @@ "tool_use_system_prompt_tokens": 395 }, "openrouter/anthropic/claude-3-sonnet": { - "display_name": "Claude 3 Sonnet", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", @@ -24843,8 +22206,6 @@ "supports_vision": true }, "openrouter/anthropic/claude-3.5-sonnet": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -24860,8 +22221,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-3.5-sonnet:beta": { - "display_name": "Claude 3.5 Sonnet Beta", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -24876,8 +22235,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-3.7-sonnet": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", @@ -24895,8 +22252,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-3.7-sonnet:beta": { - "display_name": "Claude 3.7 Sonnet Beta", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", @@ -24913,8 +22268,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-instant-v1": { - "display_name": "Claude Instant v1", - "model_vendor": "anthropic", "input_cost_per_token": 1.63e-06, "litellm_provider": "openrouter", "max_output_tokens": 8191, @@ -24924,8 +22277,6 @@ "supports_tool_choice": true }, "openrouter/anthropic/claude-opus-4": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -24946,8 +22297,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-opus-4.1": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 1.875e-05, "cache_creation_input_token_cost_above_1hr": 3e-05, @@ -24969,8 +22318,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-sonnet-4": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, @@ -24995,8 +22342,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-opus-4.5": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -25016,8 +22361,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-sonnet-4.5": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -25042,8 +22385,6 @@ "tool_use_system_prompt_tokens": 159 }, "openrouter/anthropic/claude-haiku-4.5": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, @@ -25063,8 +22404,6 @@ "tool_use_system_prompt_tokens": 346 }, "openrouter/bytedance/ui-tars-1.5-7b": { - "display_name": "UI-TARS 1.5 7B", - "model_vendor": "bytedance", "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -25076,8 +22415,6 @@ "supports_tool_choice": true }, "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { - "display_name": "Dolphin Mixtral 8x7B", - "model_vendor": "cognitivecomputations", "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 32769, @@ -25086,8 +22423,6 @@ "supports_tool_choice": true }, "openrouter/cohere/command-r-plus": { - "display_name": "Command R Plus", - "model_vendor": "cohere", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_tokens": 128000, @@ -25096,8 +22431,6 @@ "supports_tool_choice": true }, "openrouter/databricks/dbrx-instruct": { - "display_name": "DBRX Instruct", - "model_vendor": "databricks", "input_cost_per_token": 6e-07, "litellm_provider": "openrouter", "max_tokens": 32768, @@ -25106,8 +22439,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "display_name": "DeepSeek Chat", - "model_vendor": "deepseek", "input_cost_per_token": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, @@ -25119,9 +22450,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat-v3-0324": { - "display_name": "DeepSeek Chat V3 0324", - "model_vendor": "deepseek", - "model_version": "0324", "input_cost_per_token": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, @@ -25133,8 +22461,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat-v3.1": { - "display_name": "DeepSeek Chat V3.1", - "model_vendor": "deepseek", "input_cost_per_token": 2e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", @@ -25150,9 +22476,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2": { - "display_name": "DeepSeek V3.2", - "model_vendor": "deepseek", - "model_version": "v3.2", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "openrouter", @@ -25168,8 +22491,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v3.2-exp": { - "display_name": "DeepSeek V3.2 Experimental", - "model_vendor": "deepseek", "input_cost_per_token": 2e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", @@ -25185,8 +22506,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-coder": { - "display_name": "DeepSeek Coder", - "model_vendor": "deepseek", "input_cost_per_token": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 66000, @@ -25198,8 +22517,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-r1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 5.5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", @@ -25215,9 +22532,6 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-r1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "input_cost_per_token": 5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", @@ -25233,8 +22547,6 @@ "supports_tool_choice": true }, "openrouter/fireworks/firellava-13b": { - "display_name": "FireLLaVA 13B", - "model_vendor": "fireworks", "input_cost_per_token": 2e-07, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -25243,8 +22555,6 @@ "supports_tool_choice": true }, "openrouter/google/gemini-2.0-flash-001": { - "display_name": "Gemini 2.0 Flash 001", - "model_vendor": "google", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -25267,8 +22577,6 @@ "supports_vision": true }, "openrouter/google/gemini-2.5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", @@ -25291,8 +22599,6 @@ "supports_vision": true }, "openrouter/google/gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", @@ -25315,8 +22621,6 @@ "supports_vision": true }, "openrouter/google/gemini-3-pro-preview": { - "display_name": "Gemini 3 Pro Preview", - "model_vendor": "google", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -25363,9 +22667,54 @@ "supports_vision": true, "supports_web_search": true }, + "openrouter/google/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 5e-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": 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": 3e-06, + "output_cost_per_token": 3e-06, + "rpm": 2000, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_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": 800000 + }, "openrouter/google/gemini-pro-1.5": { - "display_name": "Gemini Pro 1.5", - "model_vendor": "google", "input_cost_per_image": 0.00265, "input_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", @@ -25379,8 +22728,6 @@ "supports_vision": true }, "openrouter/google/gemini-pro-vision": { - "display_name": "Gemini Pro Vision", - "model_vendor": "google", "input_cost_per_image": 0.0025, "input_cost_per_token": 1.25e-07, "litellm_provider": "openrouter", @@ -25392,8 +22739,6 @@ "supports_vision": true }, "openrouter/google/palm-2-chat-bison": { - "display_name": "PaLM 2 Chat Bison", - "model_vendor": "google", "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 25804, @@ -25402,8 +22747,6 @@ "supports_tool_choice": true }, "openrouter/google/palm-2-codechat-bison": { - "display_name": "PaLM 2 Codechat Bison", - "model_vendor": "google", "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 20070, @@ -25412,8 +22755,6 @@ "supports_tool_choice": true }, "openrouter/gryphe/mythomax-l2-13b": { - "display_name": "MythoMax L2 13B", - "model_vendor": "gryphe", "input_cost_per_token": 1.875e-06, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25422,9 +22763,6 @@ "supports_tool_choice": true }, "openrouter/jondurbin/airoboros-l2-70b-2.1": { - "display_name": "Airoboros L2 70B 2.1", - "model_vendor": "jondurbin", - "model_version": "2.1", "input_cost_per_token": 1.3875e-05, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -25433,8 +22771,6 @@ "supports_tool_choice": true }, "openrouter/mancer/weaver": { - "display_name": "Weaver", - "model_vendor": "mancer", "input_cost_per_token": 5.625e-06, "litellm_provider": "openrouter", "max_tokens": 8000, @@ -25443,8 +22779,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/codellama-34b-instruct": { - "display_name": "Code Llama 34B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25453,8 +22787,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-2-13b-chat": { - "display_name": "Llama 2 13B Chat", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -25463,8 +22795,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-2-70b-chat": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "input_cost_per_token": 1.5e-06, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -25473,8 +22803,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-3-70b-instruct": { - "display_name": "Llama 3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5.9e-07, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25483,8 +22811,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-3-70b-instruct:nitro": { - "display_name": "Llama 3 70B Instruct Nitro", - "model_vendor": "meta", "input_cost_per_token": 9e-07, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25493,8 +22819,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-3-8b-instruct:extended": { - "display_name": "Llama 3 8B Instruct Extended", - "model_vendor": "meta", "input_cost_per_token": 2.25e-07, "litellm_provider": "openrouter", "max_tokens": 16384, @@ -25503,8 +22827,6 @@ "supports_tool_choice": true }, "openrouter/meta-llama/llama-3-8b-instruct:free": { - "display_name": "Llama 3 8B Instruct Free", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25513,8 +22835,6 @@ "supports_tool_choice": true }, "openrouter/microsoft/wizardlm-2-8x22b:nitro": { - "display_name": "WizardLM 2 8x22B Nitro", - "model_vendor": "microsoft", "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_tokens": 65536, @@ -25523,27 +22843,24 @@ "supports_tool_choice": true }, "openrouter/minimax/minimax-m2": { - "display_name": "MiniMax M2", - "model_vendor": "minimax", - "input_cost_per_token": 2.55e-07, + "input_cost_per_token": 2.55e-7, "litellm_provider": "openrouter", "max_input_tokens": 204800, "max_output_tokens": 204800, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.02e-06, + "output_cost_per_token": 1.02e-6, "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/mistralai/devstral-2512:free": { - "display_name": "Mistralai Devstral 2512:free", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 262144, + "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0, @@ -25553,8 +22870,6 @@ "supports_vision": false }, "openrouter/mistralai/devstral-2512": { - "display_name": "Mistralai Devstral 2512", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 1.5e-07, "litellm_provider": "openrouter", @@ -25569,12 +22884,11 @@ "supports_vision": false }, "openrouter/mistralai/ministral-3b-2512": { - "display_name": "Mistralai Ministral 3B 2512", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, + "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, @@ -25584,12 +22898,11 @@ "supports_vision": true }, "openrouter/mistralai/ministral-8b-2512": { - "display_name": "Mistralai Ministral 8B 2512", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, + "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, @@ -25599,12 +22912,11 @@ "supports_vision": true }, "openrouter/mistralai/ministral-14b-2512": { - "display_name": "Mistralai Ministral 14B 2512", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, + "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, @@ -25614,12 +22926,11 @@ "supports_vision": true }, "openrouter/mistralai/mistral-large-2512": { - "display_name": "Mistralai Mistral Large 2512", - "model_vendor": "mistral", "input_cost_per_image": 0, "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, + "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, @@ -25629,8 +22940,6 @@ "supports_vision": true }, "openrouter/mistralai/mistral-7b-instruct": { - "display_name": "Mistral 7B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 1.3e-07, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25639,8 +22948,6 @@ "supports_tool_choice": true }, "openrouter/mistralai/mistral-7b-instruct:free": { - "display_name": "Mistral 7B Instruct Free", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25649,8 +22956,6 @@ "supports_tool_choice": true }, "openrouter/mistralai/mistral-large": { - "display_name": "Mistral Large", - "model_vendor": "mistralai", "input_cost_per_token": 8e-06, "litellm_provider": "openrouter", "max_tokens": 32000, @@ -25659,8 +22964,6 @@ "supports_tool_choice": true }, "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "display_name": "Mistral Small 3.1 24B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", "max_tokens": 32000, @@ -25669,8 +22972,6 @@ "supports_tool_choice": true }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "display_name": "Mistral Small 3.2 24B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", "max_tokens": 32000, @@ -25679,8 +22980,6 @@ "supports_tool_choice": true }, "openrouter/mistralai/mixtral-8x22b-instruct": { - "display_name": "Mixtral 8x22B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 6.5e-07, "litellm_provider": "openrouter", "max_tokens": 65536, @@ -25689,8 +22988,6 @@ "supports_tool_choice": true }, "openrouter/nousresearch/nous-hermes-llama2-13b": { - "display_name": "Nous Hermes Llama2 13B", - "model_vendor": "nousresearch", "input_cost_per_token": 2e-07, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -25699,8 +22996,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-3.5-turbo": { - "display_name": "GPT-3.5 Turbo", - "model_vendor": "openai", "input_cost_per_token": 1.5e-06, "litellm_provider": "openrouter", "max_tokens": 4095, @@ -25709,8 +23004,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-3.5-turbo-16k": { - "display_name": "GPT-3.5 Turbo 16K", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_tokens": 16383, @@ -25719,8 +23012,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-4": { - "display_name": "GPT-4", - "model_vendor": "openai", "input_cost_per_token": 3e-05, "litellm_provider": "openrouter", "max_tokens": 8192, @@ -25729,8 +23020,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-4-vision-preview": { - "display_name": "GPT-4 Vision Preview", - "model_vendor": "openai", "input_cost_per_image": 0.01445, "input_cost_per_token": 1e-05, "litellm_provider": "openrouter", @@ -25742,8 +23031,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1": { - "display_name": "GPT-4.1", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", @@ -25761,8 +23048,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1-2025-04-14": { - "display_name": "GPT-4.1", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", @@ -25780,8 +23065,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1-mini": { - "display_name": "GPT-4.1 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", @@ -25799,8 +23082,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1-mini-2025-04-14": { - "display_name": "GPT-4.1 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", @@ -25818,8 +23099,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1-nano": { - "display_name": "GPT-4.1 Nano", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -25837,8 +23116,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4.1-nano-2025-04-14": { - "display_name": "GPT-4.1 Nano", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -25856,8 +23133,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4o": { - "display_name": "GPT-4o", - "model_vendor": "openai", "input_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -25871,8 +23146,6 @@ "supports_vision": true }, "openrouter/openai/gpt-4o-2024-05-13": { - "display_name": "GPT-4o", - "model_vendor": "openai", "input_cost_per_token": 5e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -25886,8 +23159,6 @@ "supports_vision": true }, "openrouter/openai/gpt-5-chat": { - "display_name": "GPT-5 Chat", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", @@ -25907,8 +23178,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-5-codex": { - "display_name": "GPT-5 Codex", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", @@ -25928,8 +23197,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-5": { - "display_name": "GPT-5", - "model_vendor": "openai", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", @@ -25949,8 +23216,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-5-mini": { - "display_name": "GPT-5 Mini", - "model_vendor": "openai", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", @@ -25970,8 +23235,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-5-nano": { - "display_name": "GPT-5 Nano", - "model_vendor": "openai", "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, "litellm_provider": "openrouter", @@ -25991,9 +23254,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-5.2": { - "display_name": "Openai GPT 5.2", - "model_vendor": "openai", - "model_version": "5.2", "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, @@ -26010,9 +23270,6 @@ "supports_vision": true }, "openrouter/openai/gpt-5.2-chat": { - "display_name": "Openai GPT 5.2 Chat", - "model_vendor": "openai", - "model_version": "5.2", "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, @@ -26028,9 +23285,6 @@ "supports_vision": true }, "openrouter/openai/gpt-5.2-pro": { - "display_name": "Openai GPT 5.2 Pro", - "model_vendor": "openai", - "model_version": "5.2", "input_cost_per_image": 0, "input_cost_per_token": 2.1e-05, "litellm_provider": "openrouter", @@ -26038,7 +23292,7 @@ "max_output_tokens": 128000, "max_tokens": 400000, "mode": "chat", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 1.68e-04, "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, @@ -26046,8 +23300,6 @@ "supports_vision": true }, "openrouter/openai/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -26063,8 +23315,6 @@ "supports_tool_choice": true }, "openrouter/openai/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -26080,8 +23330,6 @@ "supports_tool_choice": true }, "openrouter/openai/o1": { - "display_name": "o1", - "model_vendor": "openai", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", @@ -26099,8 +23347,6 @@ "supports_vision": true }, "openrouter/openai/o1-mini": { - "display_name": "o1 Mini", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26114,8 +23360,6 @@ "supports_vision": false }, "openrouter/openai/o1-mini-2024-09-12": { - "display_name": "o1 Mini", - "model_vendor": "openai", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26129,8 +23373,6 @@ "supports_vision": false }, "openrouter/openai/o1-preview": { - "display_name": "o1 Preview", - "model_vendor": "openai", "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26144,8 +23386,6 @@ "supports_vision": false }, "openrouter/openai/o1-preview-2024-09-12": { - "display_name": "o1 Preview", - "model_vendor": "openai", "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26159,8 +23399,6 @@ "supports_vision": false }, "openrouter/openai/o3-mini": { - "display_name": "o3 Mini", - "model_vendor": "openai", "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26175,8 +23413,6 @@ "supports_vision": false }, "openrouter/openai/o3-mini-high": { - "display_name": "o3 Mini High", - "model_vendor": "openai", "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, @@ -26191,8 +23427,6 @@ "supports_vision": false }, "openrouter/pygmalionai/mythalion-13b": { - "display_name": "Mythalion 13B", - "model_vendor": "pygmalionai", "input_cost_per_token": 1.875e-06, "litellm_provider": "openrouter", "max_tokens": 4096, @@ -26201,8 +23435,6 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 33792, @@ -26213,8 +23445,6 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen-vl-plus": { - "display_name": "Qwen VL Plus", - "model_vendor": "alibaba", "input_cost_per_token": 2.1e-07, "litellm_provider": "openrouter", "max_input_tokens": 8192, @@ -26226,22 +23456,18 @@ "supports_vision": true }, "openrouter/qwen/qwen3-coder": { - "display_name": "Qwen3 Coder", - "model_vendor": "alibaba", - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 2.2e-7, "litellm_provider": "openrouter", "max_input_tokens": 262100, "max_output_tokens": 262100, "max_tokens": 262100, "mode": "chat", - "output_cost_per_token": 9.5e-07, + "output_cost_per_token": 9.5e-7, "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, "supports_function_calling": true }, "openrouter/switchpoint/router": { - "display_name": "Switchpoint Router", - "model_vendor": "switchpoint", "input_cost_per_token": 8.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -26253,8 +23479,6 @@ "supports_tool_choice": true }, "openrouter/undi95/remm-slerp-l2-13b": { - "display_name": "ReMM SLERP L2 13B", - "model_vendor": "undi95", "input_cost_per_token": 1.875e-06, "litellm_provider": "openrouter", "max_tokens": 6144, @@ -26263,8 +23487,6 @@ "supports_tool_choice": true }, "openrouter/x-ai/grok-4": { - "display_name": "Grok 4", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "openrouter", "max_input_tokens": 256000, @@ -26279,8 +23501,6 @@ "supports_web_search": true }, "openrouter/x-ai/grok-4-fast:free": { - "display_name": "Grok 4 Fast Free", - "model_vendor": "xai", "input_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 2000000, @@ -26295,38 +23515,32 @@ "supports_web_search": false }, "openrouter/z-ai/glm-4.6": { - "display_name": "GLM 4.6", - "model_vendor": "zhipu", - "input_cost_per_token": 4e-07, + "input_cost_per_token": 4.0e-7, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 202800, "mode": "chat", - "output_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.75e-6, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "openrouter/z-ai/glm-4.6:exacto": { - "display_name": "GLM 4.6 Exacto", - "model_vendor": "zhipu", - "input_cost_per_token": 4.5e-07, + "input_cost_per_token": 4.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 202800, "mode": "chat", - "output_cost_per_token": 1.9e-06, + "output_cost_per_token": 1.9e-6, "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26341,8 +23555,6 @@ "supports_tool_choice": true }, "ovhcloud/Llama-3.1-8B-Instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26356,8 +23568,6 @@ "supports_tool_choice": true }, "ovhcloud/Meta-Llama-3_1-70B-Instruct": { - "display_name": "Meta Llama 3.1 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26371,8 +23581,6 @@ "supports_tool_choice": false }, "ovhcloud/Meta-Llama-3_3-70B-Instruct": { - "display_name": "Meta Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26386,9 +23594,6 @@ "supports_tool_choice": true }, "ovhcloud/Mistral-7B-Instruct-v0.3": { - "display_name": "Mistral 7B Instruct v0.3", - "model_vendor": "mistralai", - "model_version": "0.3", "input_cost_per_token": 1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 127000, @@ -26402,9 +23607,6 @@ "supports_tool_choice": true }, "ovhcloud/Mistral-Nemo-Instruct-2407": { - "display_name": "Mistral Nemo Instruct 2407", - "model_vendor": "mistralai", - "model_version": "2407", "input_cost_per_token": 1.3e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 118000, @@ -26418,8 +23620,6 @@ "supports_tool_choice": true }, "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { - "display_name": "Mistral Small 3.2 24B Instruct 2506", - "model_vendor": "mistralai", "input_cost_per_token": 9e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 128000, @@ -26434,8 +23634,6 @@ "supports_vision": true }, "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { - "display_name": "Mixtral 8x7B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 6.3e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, @@ -26449,8 +23647,6 @@ "supports_tool_choice": false }, "ovhcloud/Qwen2.5-Coder-32B-Instruct": { - "display_name": "Qwen 2.5 Coder 32B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 8.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, @@ -26464,8 +23660,6 @@ "supports_tool_choice": false }, "ovhcloud/Qwen2.5-VL-72B-Instruct": { - "display_name": "Qwen 2.5 VL 72B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 9.1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, @@ -26480,8 +23674,6 @@ "supports_vision": true }, "ovhcloud/Qwen3-32B": { - "display_name": "Qwen3 32B", - "model_vendor": "alibaba", "input_cost_per_token": 8e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, @@ -26496,8 +23688,6 @@ "supports_tool_choice": true }, "ovhcloud/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 8e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26512,8 +23702,6 @@ "supports_tool_choice": false }, "ovhcloud/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 4e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, @@ -26528,9 +23716,6 @@ "supports_tool_choice": false }, "ovhcloud/llava-v1.6-mistral-7b-hf": { - "display_name": "LLaVA v1.6 Mistral 7B", - "model_vendor": "liuhaotian", - "model_version": "1.6", "input_cost_per_token": 2.9e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, @@ -26545,8 +23730,6 @@ "supports_vision": true }, "ovhcloud/mamba-codestral-7B-v0.1": { - "display_name": "Mamba Codestral 7B v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 1.9e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 256000, @@ -26560,8 +23743,6 @@ "supports_tool_choice": false }, "palm/chat-bison": { - "display_name": "PaLM Chat Bison", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26572,8 +23753,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "palm/chat-bison-001": { - "display_name": "PaLM Chat Bison 001", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26584,8 +23763,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "palm/text-bison": { - "display_name": "PaLM Text Bison", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26596,8 +23773,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "palm/text-bison-001": { - "display_name": "PaLM Text Bison 001", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26608,8 +23783,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "palm/text-bison-safety-off": { - "display_name": "PaLM Text Bison Safety Off", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26620,8 +23793,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "palm/text-bison-safety-recitation-off": { - "display_name": "PaLM Text Bison Safety Recitation Off", - "model_vendor": "google", "input_cost_per_token": 1.25e-07, "litellm_provider": "palm", "max_input_tokens": 8192, @@ -26632,22 +23803,16 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "parallel_ai/search": { - "display_name": "Parallel AI Search", - "model_vendor": "parallel_ai", "input_cost_per_query": 0.004, "litellm_provider": "parallel_ai", "mode": "search" }, "parallel_ai/search-pro": { - "display_name": "Parallel AI Search Pro", - "model_vendor": "parallel_ai", "input_cost_per_query": 0.009, "litellm_provider": "parallel_ai", "mode": "search" }, "perplexity/codellama-34b-instruct": { - "display_name": "Code Llama 34B Instruct", - "model_vendor": "meta", "input_cost_per_token": 3.5e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, @@ -26657,8 +23822,6 @@ "output_cost_per_token": 1.4e-06 }, "perplexity/codellama-70b-instruct": { - "display_name": "Code Llama 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, @@ -26668,8 +23831,6 @@ "output_cost_per_token": 2.8e-06 }, "perplexity/llama-2-70b-chat": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 4096, @@ -26679,8 +23840,6 @@ "output_cost_per_token": 2.8e-06 }, "perplexity/llama-3.1-70b-instruct": { - "display_name": "Llama 3.1 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 131072, @@ -26690,8 +23849,6 @@ "output_cost_per_token": 1e-06 }, "perplexity/llama-3.1-8b-instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "perplexity", "max_input_tokens": 131072, @@ -26701,8 +23858,6 @@ "output_cost_per_token": 2e-07 }, "perplexity/llama-3.1-sonar-huge-128k-online": { - "display_name": "Llama 3.1 Sonar Huge 128K Online", - "model_vendor": "perplexity", "deprecation_date": "2025-02-22", "input_cost_per_token": 5e-06, "litellm_provider": "perplexity", @@ -26713,8 +23868,6 @@ "output_cost_per_token": 5e-06 }, "perplexity/llama-3.1-sonar-large-128k-chat": { - "display_name": "Llama 3.1 Sonar Large 128K Chat", - "model_vendor": "perplexity", "deprecation_date": "2025-02-22", "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", @@ -26725,8 +23878,6 @@ "output_cost_per_token": 1e-06 }, "perplexity/llama-3.1-sonar-large-128k-online": { - "display_name": "Llama 3.1 Sonar Large 128K Online", - "model_vendor": "perplexity", "deprecation_date": "2025-02-22", "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", @@ -26737,8 +23888,6 @@ "output_cost_per_token": 1e-06 }, "perplexity/llama-3.1-sonar-small-128k-chat": { - "display_name": "Llama 3.1 Sonar Small 128K Chat", - "model_vendor": "perplexity", "deprecation_date": "2025-02-22", "input_cost_per_token": 2e-07, "litellm_provider": "perplexity", @@ -26749,8 +23898,6 @@ "output_cost_per_token": 2e-07 }, "perplexity/llama-3.1-sonar-small-128k-online": { - "display_name": "Llama 3.1 Sonar Small 128K Online", - "model_vendor": "perplexity", "deprecation_date": "2025-02-22", "input_cost_per_token": 2e-07, "litellm_provider": "perplexity", @@ -26761,8 +23908,6 @@ "output_cost_per_token": 2e-07 }, "perplexity/mistral-7b-instruct": { - "display_name": "Mistral 7B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 4096, @@ -26772,8 +23917,6 @@ "output_cost_per_token": 2.8e-07 }, "perplexity/mixtral-8x7b-instruct": { - "display_name": "Mixtral 8x7B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 4096, @@ -26783,8 +23926,6 @@ "output_cost_per_token": 2.8e-07 }, "perplexity/pplx-70b-chat": { - "display_name": "PPLX 70B Chat", - "model_vendor": "perplexity", "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 4096, @@ -26794,8 +23935,6 @@ "output_cost_per_token": 2.8e-06 }, "perplexity/pplx-70b-online": { - "display_name": "PPLX 70B Online", - "model_vendor": "perplexity", "input_cost_per_request": 0.005, "input_cost_per_token": 0.0, "litellm_provider": "perplexity", @@ -26806,8 +23945,6 @@ "output_cost_per_token": 2.8e-06 }, "perplexity/pplx-7b-chat": { - "display_name": "PPLX 7B Chat", - "model_vendor": "perplexity", "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 8192, @@ -26817,8 +23954,6 @@ "output_cost_per_token": 2.8e-07 }, "perplexity/pplx-7b-online": { - "display_name": "PPLX 7B Online", - "model_vendor": "perplexity", "input_cost_per_request": 0.005, "input_cost_per_token": 0.0, "litellm_provider": "perplexity", @@ -26829,8 +23964,6 @@ "output_cost_per_token": 2.8e-07 }, "perplexity/sonar": { - "display_name": "Sonar", - "model_vendor": "perplexity", "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, @@ -26845,8 +23978,6 @@ "supports_web_search": true }, "perplexity/sonar-deep-research": { - "display_name": "Sonar Deep Research", - "model_vendor": "perplexity", "citation_cost_per_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", @@ -26864,8 +23995,6 @@ "supports_web_search": true }, "perplexity/sonar-medium-chat": { - "display_name": "Sonar Medium Chat", - "model_vendor": "perplexity", "input_cost_per_token": 6e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, @@ -26875,8 +24004,6 @@ "output_cost_per_token": 1.8e-06 }, "perplexity/sonar-medium-online": { - "display_name": "Sonar Medium Online", - "model_vendor": "perplexity", "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", @@ -26887,8 +24014,6 @@ "output_cost_per_token": 1.8e-06 }, "perplexity/sonar-pro": { - "display_name": "Sonar Pro", - "model_vendor": "perplexity", "input_cost_per_token": 3e-06, "litellm_provider": "perplexity", "max_input_tokens": 200000, @@ -26904,8 +24029,6 @@ "supports_web_search": true }, "perplexity/sonar-reasoning": { - "display_name": "Sonar Reasoning", - "model_vendor": "perplexity", "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, @@ -26921,8 +24044,6 @@ "supports_web_search": true }, "perplexity/sonar-reasoning-pro": { - "display_name": "Sonar Reasoning Pro", - "model_vendor": "perplexity", "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, @@ -26938,8 +24059,6 @@ "supports_web_search": true }, "perplexity/sonar-small-chat": { - "display_name": "Sonar Small Chat", - "model_vendor": "perplexity", "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 16384, @@ -26949,8 +24068,6 @@ "output_cost_per_token": 2.8e-07 }, "perplexity/sonar-small-online": { - "display_name": "Sonar Small Online", - "model_vendor": "perplexity", "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", @@ -26961,8 +24078,6 @@ "output_cost_per_token": 2.8e-07 }, "publicai/swiss-ai/apertus-8b-instruct": { - "display_name": "Apertus 8B Instruct", - "model_vendor": "swiss_ai", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, @@ -26975,8 +24090,6 @@ "supports_tool_choice": true }, "publicai/swiss-ai/apertus-70b-instruct": { - "display_name": "Apertus 70B Instruct", - "model_vendor": "swiss_ai", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, @@ -26989,8 +24102,6 @@ "supports_tool_choice": true }, "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { - "display_name": "Gemma SEA-LION v4 27B IT", - "model_vendor": "aisingapore", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, @@ -27003,8 +24114,6 @@ "supports_tool_choice": true }, "publicai/BSC-LT/salamandra-7b-instruct-tools-16k": { - "display_name": "Salamandra 7B Instruct Tools 16K", - "model_vendor": "bsc_lt", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 16384, @@ -27017,8 +24126,6 @@ "supports_tool_choice": true }, "publicai/BSC-LT/ALIA-40b-instruct_Q8_0": { - "display_name": "ALIA 40B Instruct Q8", - "model_vendor": "bsc_lt", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, @@ -27031,8 +24138,6 @@ "supports_tool_choice": true }, "publicai/allenai/Olmo-3-7B-Instruct": { - "display_name": "Olmo 3 7B Instruct", - "model_vendor": "allenai", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, @@ -27045,8 +24150,6 @@ "supports_tool_choice": true }, "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { - "display_name": "Qwen SEA-LION v4 32B IT", - "model_vendor": "aisingapore", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, @@ -27059,8 +24162,6 @@ "supports_tool_choice": true }, "publicai/allenai/Olmo-3-7B-Think": { - "display_name": "Olmo 3 7B Think", - "model_vendor": "allenai", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, @@ -27074,8 +24175,6 @@ "supports_reasoning": true }, "publicai/allenai/Olmo-3-32B-Think": { - "display_name": "Olmo 3 32B Think", - "model_vendor": "allenai", "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, @@ -27089,8 +24188,6 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { - "display_name": "Qwen3 Coder 480B A35B v1", - "model_vendor": "alibaba", "input_cost_per_token": 2.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262000, @@ -27103,8 +24200,6 @@ "supports_tool_choice": true }, "qwen.qwen3-235b-a22b-2507-v1:0": { - "display_name": "Qwen3 235B A22B 2507 v1", - "model_vendor": "alibaba", "input_cost_per_token": 2.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, @@ -27117,36 +24212,30 @@ "supports_tool_choice": true }, "qwen.qwen3-coder-30b-a3b-v1:0": { - "display_name": "Qwen3 Coder 30B A3B v1", - "model_vendor": "alibaba", "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": 6e-07, + "output_cost_per_token": 6.0e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen.qwen3-32b-v1:0": { - "display_name": "Qwen3 32B v1", - "model_vendor": "alibaba", "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": 6e-07, + "output_cost_per_token": 6.0e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen.qwen3-next-80b-a3b": { - "display_name": "Qwen3 Next 80B A3b", - "model_vendor": "alibaba", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -27158,8 +24247,6 @@ "supports_system_messages": true }, "qwen.qwen3-vl-235b-a22b": { - "display_name": "Qwen3 VL 235B A22b", - "model_vendor": "alibaba", "input_cost_per_token": 5.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -27172,8 +24259,6 @@ "supports_vision": true }, "recraft/recraftv2": { - "display_name": "Recraft v2", - "model_vendor": "recraft", "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.022, @@ -27183,8 +24268,6 @@ ] }, "recraft/recraftv3": { - "display_name": "Recraft v3", - "model_vendor": "recraft", "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.04, @@ -27194,8 +24277,6 @@ ] }, "replicate/meta/llama-2-13b": { - "display_name": "Llama 2 13B", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27206,8 +24287,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-2-13b-chat": { - "display_name": "Llama 2 13B Chat", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27218,8 +24297,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-2-70b": { - "display_name": "Llama 2 70B", - "model_vendor": "meta", "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27230,8 +24307,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-2-70b-chat": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27242,8 +24317,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-2-7b": { - "display_name": "Llama 2 7B", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27254,8 +24327,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-2-7b-chat": { - "display_name": "Llama 2 7B Chat", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27266,8 +24337,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-3-70b": { - "display_name": "Llama 3 70B", - "model_vendor": "meta", "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 8192, @@ -27278,8 +24347,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-3-70b-instruct": { - "display_name": "Llama 3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 8192, @@ -27290,8 +24357,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-3-8b": { - "display_name": "Llama 3 8B", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 8086, @@ -27302,8 +24367,6 @@ "supports_tool_choice": true }, "replicate/meta/llama-3-8b-instruct": { - "display_name": "Llama 3 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 8086, @@ -27314,9 +24377,6 @@ "supports_tool_choice": true }, "replicate/mistralai/mistral-7b-instruct-v0.2": { - "display_name": "Mistral 7B Instruct v0.2", - "model_vendor": "mistralai", - "model_version": "0.2", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27327,8 +24387,6 @@ "supports_tool_choice": true }, "replicate/mistralai/mistral-7b-v0.1": { - "display_name": "Mistral 7B v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27339,8 +24397,6 @@ "supports_tool_choice": true }, "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { - "display_name": "Mixtral 8x7B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, @@ -27351,8 +24407,6 @@ "supports_tool_choice": true }, "rerank-english-v2.0": { - "display_name": "Rerank English v2.0", - "model_vendor": "cohere", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", @@ -27364,8 +24418,6 @@ "output_cost_per_token": 0.0 }, "rerank-english-v3.0": { - "display_name": "Rerank English v3.0", - "model_vendor": "cohere", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", @@ -27377,8 +24429,6 @@ "output_cost_per_token": 0.0 }, "rerank-multilingual-v2.0": { - "display_name": "Rerank Multilingual v2.0", - "model_vendor": "cohere", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", @@ -27390,8 +24440,6 @@ "output_cost_per_token": 0.0 }, "rerank-multilingual-v3.0": { - "display_name": "Rerank Multilingual v3.0", - "model_vendor": "cohere", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", @@ -27403,8 +24451,6 @@ "output_cost_per_token": 0.0 }, "rerank-v3.5": { - "display_name": "Rerank v3.5", - "model_vendor": "cohere", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", @@ -27416,8 +24462,6 @@ "output_cost_per_token": 0.0 }, "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { - "display_name": "NV RerankQA Mistral 4B v3", - "model_vendor": "nvidia", "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", @@ -27425,8 +24469,6 @@ "output_cost_per_token": 0.0 }, "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": { - "display_name": "Llama 3.2 NV RerankQA 1B v2", - "model_vendor": "nvidia", "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", @@ -27434,9 +24476,6 @@ "output_cost_per_token": 0.0 }, "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2": { - "display_name": "Llama 3.2 Nv Rerankqa 1B V2", - "model_vendor": "meta", - "model_version": "3.2", "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", @@ -27444,8 +24483,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-13b": { - "display_name": "Llama 2 13B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27455,8 +24492,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-13b-f": { - "display_name": "Llama 2 13B F", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27466,8 +24501,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-70b": { - "display_name": "Llama 2 70B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27477,8 +24510,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-70b-b-f": { - "display_name": "Llama 2 70B B F", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27488,8 +24519,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-7b": { - "display_name": "Llama 2 7B", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27499,8 +24528,6 @@ "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-7b-f": { - "display_name": "Llama 2 7B F", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, @@ -27510,8 +24537,6 @@ "output_cost_per_token": 0.0 }, "sambanova/DeepSeek-R1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", "max_input_tokens": 32768, @@ -27522,8 +24547,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "input_cost_per_token": 7e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, @@ -27534,8 +24557,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", "input_cost_per_token": 3e-06, "litellm_provider": "sambanova", "max_input_tokens": 32768, @@ -27549,8 +24570,6 @@ "supports_tool_choice": true }, "sambanova/Llama-4-Maverick-17B-128E-Instruct": { - "display_name": "Llama 4 Maverick 17B 128E Instruct", - "model_vendor": "meta", "input_cost_per_token": 6.3e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, @@ -27568,8 +24587,6 @@ "supports_vision": true }, "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -27586,8 +24603,6 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-405B-Instruct": { - "display_name": "Meta Llama 3.1 405B Instruct", - "model_vendor": "meta", "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -27601,8 +24616,6 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-8B-Instruct": { - "display_name": "Meta Llama 3.1 8B Instruct", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -27616,8 +24629,6 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.2-1B-Instruct": { - "display_name": "Meta Llama 3.2 1B Instruct", - "model_vendor": "meta", "input_cost_per_token": 4e-08, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -27628,8 +24639,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Meta-Llama-3.2-3B-Instruct": { - "display_name": "Meta Llama 3.2 3B Instruct", - "model_vendor": "meta", "input_cost_per_token": 8e-08, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -27640,8 +24649,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Meta-Llama-3.3-70B-Instruct": { - "display_name": "Meta Llama 3.3 70B Instruct", - "model_vendor": "meta", "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, @@ -27655,8 +24662,6 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-Guard-3-8B": { - "display_name": "Meta Llama Guard 3 8B", - "model_vendor": "meta", "input_cost_per_token": 3e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -27667,8 +24672,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/QwQ-32B": { - "display_name": "QwQ 32B", - "model_vendor": "alibaba", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -27679,8 +24682,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Qwen2-Audio-7B-Instruct": { - "display_name": "Qwen2 Audio 7B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -27692,8 +24693,6 @@ "supports_audio_input": true }, "sambanova/Qwen3-32B": { - "display_name": "Qwen3 32B", - "model_vendor": "alibaba", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -27707,8 +24706,6 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "display_name": "DeepSeek V3.1", - "model_vendor": "deepseek", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -27722,8 +24719,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -27736,9 +24731,8 @@ "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "snowflake/claude-3-5-sonnet": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "litellm_provider": "snowflake", "max_input_tokens": 18000, "max_output_tokens": 8192, @@ -27747,8 +24741,6 @@ "supports_computer_use": true }, "snowflake/deepseek-r1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "litellm_provider": "snowflake", "max_input_tokens": 32768, "max_output_tokens": 8192, @@ -27757,8 +24749,6 @@ "supports_reasoning": true }, "snowflake/gemma-7b": { - "display_name": "Gemma 7B", - "model_vendor": "google", "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, @@ -27766,8 +24756,6 @@ "mode": "chat" }, "snowflake/jamba-1.5-large": { - "display_name": "Jamba 1.5 Large", - "model_vendor": "ai21", "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, @@ -27775,8 +24763,6 @@ "mode": "chat" }, "snowflake/jamba-1.5-mini": { - "display_name": "Jamba 1.5 Mini", - "model_vendor": "ai21", "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, @@ -27784,8 +24770,6 @@ "mode": "chat" }, "snowflake/jamba-instruct": { - "display_name": "Jamba Instruct", - "model_vendor": "ai21", "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, @@ -27793,8 +24777,6 @@ "mode": "chat" }, "snowflake/llama2-70b-chat": { - "display_name": "Llama 2 70B Chat", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, @@ -27802,8 +24784,6 @@ "mode": "chat" }, "snowflake/llama3-70b": { - "display_name": "Llama 3 70B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, @@ -27811,8 +24791,6 @@ "mode": "chat" }, "snowflake/llama3-8b": { - "display_name": "Llama 3 8B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, @@ -27820,8 +24798,6 @@ "mode": "chat" }, "snowflake/llama3.1-405b": { - "display_name": "Llama 3.1 405B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27829,8 +24805,6 @@ "mode": "chat" }, "snowflake/llama3.1-70b": { - "display_name": "Llama 3.1 70B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27838,8 +24812,6 @@ "mode": "chat" }, "snowflake/llama3.1-8b": { - "display_name": "Llama 3.1 8B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27847,8 +24819,6 @@ "mode": "chat" }, "snowflake/llama3.2-1b": { - "display_name": "Llama 3.2 1B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27856,8 +24826,6 @@ "mode": "chat" }, "snowflake/llama3.2-3b": { - "display_name": "Llama 3.2 3B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27865,8 +24833,6 @@ "mode": "chat" }, "snowflake/llama3.3-70b": { - "display_name": "Llama 3.3 70B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27874,8 +24840,6 @@ "mode": "chat" }, "snowflake/mistral-7b": { - "display_name": "Mistral 7B", - "model_vendor": "mistralai", "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, @@ -27883,8 +24847,6 @@ "mode": "chat" }, "snowflake/mistral-large": { - "display_name": "Mistral Large", - "model_vendor": "mistralai", "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, @@ -27892,8 +24854,6 @@ "mode": "chat" }, "snowflake/mistral-large2": { - "display_name": "Mistral Large 2", - "model_vendor": "mistralai", "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, @@ -27901,8 +24861,6 @@ "mode": "chat" }, "snowflake/mixtral-8x7b": { - "display_name": "Mixtral 8x7B", - "model_vendor": "mistralai", "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, @@ -27910,8 +24868,6 @@ "mode": "chat" }, "snowflake/reka-core": { - "display_name": "Reka Core", - "model_vendor": "reka", "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, @@ -27919,8 +24875,6 @@ "mode": "chat" }, "snowflake/reka-flash": { - "display_name": "Reka Flash", - "model_vendor": "reka", "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, @@ -27928,8 +24882,6 @@ "mode": "chat" }, "snowflake/snowflake-arctic": { - "display_name": "Snowflake Arctic", - "model_vendor": "snowflake", "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, @@ -27937,8 +24889,6 @@ "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { - "display_name": "Snowflake Llama 3.1 405B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, @@ -27946,8 +24896,6 @@ "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { - "display_name": "Snowflake Llama 3.3 70B", - "model_vendor": "meta", "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, @@ -27955,98 +24903,144 @@ "mode": "chat" }, "stability/sd3": { - "display_name": "SD3", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3-large": { - "display_name": "SD3 Large", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3-large-turbo": { - "display_name": "SD3 Large Turbo", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3-medium": { - "display_name": "SD3 Medium", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3.5-large": { - "display_name": "Sd3.5 Large", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3.5-large-turbo": { - "display_name": "Sd3.5 Large Turbo", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/sd3.5-medium": { - "display_name": "Sd3.5 Medium", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability/stable-image-ultra": { - "display_name": "Stable Image Ultra", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.08, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] + }, + "stability/inpaint": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/outpaint": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.004, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/erase": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/search-and-replace": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/search-and-recolor": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/remove-background": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/replace-background-and-relight": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.008, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/sketch": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/structure": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/style": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.005, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/style-transfer": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.008, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/fast": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.002, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/conservative": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.04, + "supported_endpoints": ["/v1/images/edits"] + }, + "stability/creative": { + "litellm_provider": "stability", + "mode": "image_edit", + "output_cost_per_image": 0.06, + "supported_endpoints": ["/v1/images/edits"] }, "stability/stable-image-core": { - "display_name": "Stable Image Core", - "model_vendor": "stability", "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.03, - "supported_endpoints": [ - "/v1/images/generations" - ] + "supported_endpoints": ["/v1/images/generations"] }, "stability.sd3-5-large-v1:0": { - "display_name": "Stable Diffusion 3.5 Large v1", - "model_vendor": "stability_ai", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -28054,8 +25048,6 @@ "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { - "display_name": "Stable Diffusion 3 Large v1", - "model_vendor": "stability_ai", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -28063,18 +25055,91 @@ "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { - "display_name": "Stable Image Core v1.0", - "model_vendor": "stability_ai", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, + "stability.stable-conservative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.40 + }, + "stability.stable-creative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.60 + }, + "stability.stable-fast-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.03 + }, + "stability.stable-outpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.06 + }, + "stability.stable-image-control-sketch-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-control-structure-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-erase-object-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-inpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-remove-background-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-search-recolor-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-search-replace-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-image-style-guide-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07 + }, + "stability.stable-style-transfer-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.08 + }, "stability.stable-image-core-v1:1": { - "display_name": "Stable Image Core v1.1", - "model_vendor": "stability_ai", - "model_version": "1.1", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -28082,8 +25147,6 @@ "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { - "display_name": "Stable Image Ultra v1.0", - "model_vendor": "stability_ai", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -28091,9 +25154,6 @@ "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { - "display_name": "Stable Image Ultra v1.1", - "model_vendor": "stability_ai", - "model_version": "1.1", "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -28101,46 +25161,44 @@ "output_cost_per_image": 0.14 }, "standard/1024-x-1024/dall-e-3": { - "display_name": "DALL-E 3 Standard 1024x1024", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 Standard 1024x1792", - "model_vendor": "openai", "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": { - "display_name": "DALL-E 3 Standard 1792x1024", - "model_vendor": "openai", "input_cost_per_pixel": 4.359e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0 }, + "linkup/search": { + "input_cost_per_query": 5.87e-03, + "litellm_provider": "linkup", + "mode": "search" + }, + "linkup/search-deep": { + "input_cost_per_query": 58.67e-03, + "litellm_provider": "linkup", + "mode": "search" + }, "tavily/search": { - "display_name": "Tavily Search", - "model_vendor": "tavily", "input_cost_per_query": 0.008, "litellm_provider": "tavily", "mode": "search" }, "tavily/search-advanced": { - "display_name": "Tavily Search Advanced", - "model_vendor": "tavily", "input_cost_per_query": 0.016, "litellm_provider": "tavily", "mode": "search" }, "text-bison": { - "display_name": "Text Bison", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, @@ -28151,8 +25209,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-bison32k": { - "display_name": "Text Bison 32K", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-text-models", @@ -28165,8 +25221,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-bison32k@002": { - "display_name": "Text Bison 32K @002", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-text-models", @@ -28179,8 +25233,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-bison@001": { - "display_name": "Text Bison @001", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, @@ -28191,8 +25243,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-bison@002": { - "display_name": "Text Bison @002", - "model_vendor": "google", "input_cost_per_character": 2.5e-07, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, @@ -28203,9 +25253,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-completion-codestral/codestral-2405": { - "display_name": "Codestral 2405", - "model_vendor": "mistralai", - "model_version": "2405", "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, @@ -28216,8 +25263,6 @@ "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-completion-codestral/codestral-latest": { - "display_name": "Codestral Latest", - "model_vendor": "mistralai", "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, @@ -28228,8 +25273,7 @@ "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-embedding-004": { - "display_name": "Text Embedding 004", - "model_vendor": "google", + "deprecation_date": "2026-01-14", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28241,8 +25285,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-005": { - "display_name": "Text Embedding 005", - "model_vendor": "google", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28254,8 +25296,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-3-large": { - "display_name": "Text Embedding 3 Large", - "model_vendor": "openai", "input_cost_per_token": 1.3e-07, "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", @@ -28267,8 +25307,6 @@ "output_vector_size": 3072 }, "text-embedding-3-small": { - "display_name": "Text Embedding 3 Small", - "model_vendor": "openai", "input_cost_per_token": 2e-08, "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", @@ -28280,9 +25318,6 @@ "output_vector_size": 1536 }, "text-embedding-ada-002": { - "display_name": "Text Embedding Ada 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, @@ -28292,9 +25327,6 @@ "output_vector_size": 1536 }, "text-embedding-ada-002-v2": { - "display_name": "Text Embedding Ada 002 v2", - "model_vendor": "openai", - "model_version": "002-v2", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", @@ -28305,8 +25337,6 @@ "output_cost_per_token_batches": 0.0 }, "text-embedding-large-exp-03-07": { - "display_name": "Text Embedding Large Exp 03-07", - "model_vendor": "google", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28318,8 +25348,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-preview-0409": { - "display_name": "Text Embedding Preview 0409", - "model_vendor": "google", "input_cost_per_token": 6.25e-09, "input_cost_per_token_batch_requests": 5e-09, "litellm_provider": "vertex_ai-embedding-models", @@ -28331,9 +25359,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "text-moderation-007": { - "display_name": "Text Moderation 007", - "model_vendor": "openai", - "model_version": "007", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -28343,8 +25368,6 @@ "output_cost_per_token": 0.0 }, "text-moderation-latest": { - "display_name": "Text Moderation Latest", - "model_vendor": "openai", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -28354,8 +25377,6 @@ "output_cost_per_token": 0.0 }, "text-moderation-stable": { - "display_name": "Text Moderation Stable", - "model_vendor": "openai", "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, @@ -28365,9 +25386,6 @@ "output_cost_per_token": 0.0 }, "text-multilingual-embedding-002": { - "display_name": "Text Multilingual Embedding 002", - "model_vendor": "google", - "model_version": "002", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28379,8 +25397,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-multilingual-embedding-preview-0409": { - "display_name": "Text Multilingual Embedding Preview 0409", - "model_vendor": "google", "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, @@ -28391,8 +25407,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-unicorn": { - "display_name": "Text Unicorn", - "model_vendor": "google", "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, @@ -28403,9 +25417,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-unicorn@001": { - "display_name": "Text Unicorn 001", - "model_vendor": "google", - "model_version": "001", "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, @@ -28416,8 +25427,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "textembedding-gecko": { - "display_name": "Text Embedding Gecko", - "model_vendor": "google", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28429,8 +25438,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "textembedding-gecko-multilingual": { - "display_name": "Text Embedding Gecko Multilingual", - "model_vendor": "google", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28442,9 +25449,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "textembedding-gecko-multilingual@001": { - "display_name": "Text Embedding Gecko Multilingual 001", - "model_vendor": "google", - "model_version": "001", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28456,9 +25460,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "textembedding-gecko@001": { - "display_name": "Text Embedding Gecko 001", - "model_vendor": "google", - "model_version": "001", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28470,9 +25471,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "textembedding-gecko@003": { - "display_name": "Text Embedding Gecko 003", - "model_vendor": "google", - "model_version": "003", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -28484,32 +25482,24 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "together-ai-21.1b-41b": { - "display_name": "Together AI 21.1B-41B", - "model_vendor": "together_ai", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-07 }, "together-ai-4.1b-8b": { - "display_name": "Together AI 4.1B-8B", - "model_vendor": "together_ai", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-07 }, "together-ai-41.1b-80b": { - "display_name": "Together AI 41.1B-80B", - "model_vendor": "together_ai", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 9e-07 }, "together-ai-8.1b-21b": { - "display_name": "Together AI 8.1B-21B", - "model_vendor": "together_ai", "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_tokens": 1000, @@ -28517,32 +25507,24 @@ "output_cost_per_token": 3e-07 }, "together-ai-81.1b-110b": { - "display_name": "Together AI 81.1B-110B", - "model_vendor": "together_ai", "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": { - "display_name": "Together AI Embedding 151M-350M", - "model_vendor": "together_ai", "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": { - "display_name": "Together AI Embedding Up to 150M", - "model_vendor": "together_ai", "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", "mode": "embedding", "output_cost_per_token": 0.0 }, "together_ai/baai/bge-base-en-v1.5": { - "display_name": "BGE Base EN v1.5", - "model_vendor": "baai", "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", "max_input_tokens": 512, @@ -28551,8 +25533,6 @@ "output_vector_size": 768 }, "together_ai/BAAI/bge-base-en-v1.5": { - "display_name": "BGE Base EN v1.5", - "model_vendor": "baai", "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", "max_input_tokens": 512, @@ -28561,34 +25541,28 @@ "output_vector_size": 768 }, "together-ai-up-to-4b": { - "display_name": "Together AI Up to 4B", - "model_vendor": "together_ai", "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": { - "display_name": "Qwen 2.5 72B Instruct Turbo", - "model_vendor": "alibaba", "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/Qwen/Qwen2.5-7B-Instruct-Turbo": { - "display_name": "Qwen 2.5 7B Instruct Turbo", - "model_vendor": "alibaba", "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/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "display_name": "Qwen 3 235B A22B Instruct 2507", - "model_vendor": "alibaba", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 262000, @@ -28597,11 +25571,10 @@ "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "display_name": "Qwen 3 235B A22B Thinking 2507", - "model_vendor": "alibaba", "input_cost_per_token": 6.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 256000, @@ -28610,11 +25583,10 @@ "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "display_name": "Qwen 3 235B A22B FP8", - "model_vendor": "alibaba", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 40000, @@ -28626,8 +25598,6 @@ "supports_tool_choice": false }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "display_name": "Qwen 3 Coder 480B A35B Instruct FP8", - "model_vendor": "alibaba", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 256000, @@ -28636,11 +25606,10 @@ "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-R1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 128000, @@ -28650,12 +25619,10 @@ "output_cost_per_token": 7e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", - "model_version": "0528", "input_cost_per_token": 5.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 128000, @@ -28664,11 +25631,10 @@ "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 65536, @@ -28678,11 +25644,10 @@ "output_cost_per_token": 1.25e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V3.1": { - "display_name": "DeepSeek V3.1", - "model_vendor": "deepseek", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_tokens": 128000, @@ -28695,17 +25660,14 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "display_name": "Llama 3.2 3B Instruct Turbo", - "model_vendor": "meta", "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/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "display_name": "Llama 3.3 70B Instruct Turbo", - "model_vendor": "meta", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -28716,8 +25678,6 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "display_name": "Llama 3.3 70B Instruct Turbo Free", - "model_vendor": "meta", "input_cost_per_token": 0, "litellm_provider": "together_ai", "mode": "chat", @@ -28728,41 +25688,36 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "display_name": "Llama 4 Maverick 17B 128E Instruct FP8", - "model_vendor": "meta", "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_response_schema": true, "supports_tool_choice": true }, "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "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_response_schema": true, "supports_tool_choice": true }, "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "display_name": "Meta Llama 3.1 405B Instruct Turbo", - "model_vendor": "meta", "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_response_schema": true, "supports_tool_choice": true }, "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "display_name": "Meta Llama 3.1 70B Instruct Turbo", - "model_vendor": "meta", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -28773,8 +25728,6 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "display_name": "Meta Llama 3.1 8B Instruct Turbo", - "model_vendor": "meta", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -28785,8 +25738,6 @@ "supports_tool_choice": true }, "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "display_name": "Mistral 7B Instruct v0.1", - "model_vendor": "mistralai", "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, @@ -28795,9 +25746,6 @@ "supports_tool_choice": true }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "display_name": "Mistral Small 24B Instruct 2501", - "model_vendor": "mistralai", - "model_version": "2501", "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, @@ -28805,8 +25753,6 @@ "supports_tool_choice": true }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "display_name": "Mixtral 8x7B Instruct v0.1", - "model_vendor": "mistralai", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -28817,9 +25763,6 @@ "supports_tool_choice": true }, "together_ai/moonshotai/Kimi-K2-Instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", - "model_version": "k2", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -28827,11 +25770,10 @@ "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/openai/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 128000, @@ -28840,11 +25782,10 @@ "source": "https://www.together.ai/models/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 128000, @@ -28853,11 +25794,10 @@ "source": "https://www.together.ai/models/gpt-oss-20b", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { - "display_name": "CodeLlama 34B Instruct", - "model_vendor": "meta", "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, @@ -28865,8 +25805,6 @@ "supports_tool_choice": true }, "together_ai/zai-org/GLM-4.5-Air-FP8": { - "display_name": "GLM 4.5 Air FP8", - "model_vendor": "zhipu", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 128000, @@ -28875,12 +25813,11 @@ "source": "https://www.together.ai/models/glm-4-5-air", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/zai-org/GLM-4.6": { - "display_name": "GLM 4.6", - "model_vendor": "zhipu", - "input_cost_per_token": 6e-07, + "input_cost_per_token": 0.6e-06, "litellm_provider": "together_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, @@ -28894,9 +25831,6 @@ "supports_tool_choice": true }, "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "display_name": "Kimi K2 Instruct 0905", - "model_vendor": "moonshot", - "model_version": "k2-0905", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -28908,8 +25842,6 @@ "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "display_name": "Qwen 3 Next 80B A3B Instruct", - "model_vendor": "alibaba", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -28918,11 +25850,10 @@ "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "display_name": "Qwen 3 Next 80B A3B Thinking", - "model_vendor": "alibaba", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -28931,11 +25862,10 @@ "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "tts-1": { - "display_name": "TTS 1", - "model_vendor": "openai", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -28944,9 +25874,6 @@ ] }, "tts-1-hd": { - "display_name": "TTS 1 HD", - "model_vendor": "openai", - "model_version": "1-hd", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -28954,9 +25881,43 @@ "/v1/audio/speech" ] }, + "aws_polly/standard": { + "input_cost_per_character": 4e-06, + "litellm_provider": "aws_polly", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "source": "https://aws.amazon.com/polly/pricing/" + }, + "aws_polly/neural": { + "input_cost_per_character": 1.6e-05, + "litellm_provider": "aws_polly", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "source": "https://aws.amazon.com/polly/pricing/" + }, + "aws_polly/long-form": { + "input_cost_per_character": 1e-04, + "litellm_provider": "aws_polly", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "source": "https://aws.amazon.com/polly/pricing/" + }, + "aws_polly/generative": { + "input_cost_per_character": 3e-05, + "litellm_provider": "aws_polly", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "source": "https://aws.amazon.com/polly/pricing/" + }, "us.amazon.nova-lite-v1:0": { - "display_name": "Amazon Nova Lite v1 US", - "model_vendor": "amazon", "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -28971,8 +25932,6 @@ "supports_vision": true }, "us.amazon.nova-micro-v1:0": { - "display_name": "Amazon Nova Micro v1 US", - "model_vendor": "amazon", "input_cost_per_token": 3.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -28985,8 +25944,6 @@ "supports_response_schema": true }, "us.amazon.nova-premier-v1:0": { - "display_name": "Amazon Nova Premier v1 US", - "model_vendor": "amazon", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, @@ -29001,8 +25958,6 @@ "supports_vision": true }, "us.amazon.nova-pro-v1:0": { - "display_name": "Amazon Nova Pro v1 US", - "model_vendor": "amazon", "input_cost_per_token": 8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -29017,9 +25972,6 @@ "supports_vision": true }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", - "model_version": "20241022", "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, @@ -29037,9 +25989,6 @@ "supports_tool_choice": true }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, @@ -29062,9 +26011,6 @@ "tool_use_system_prompt_tokens": 346 }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240620", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -29079,9 +26025,6 @@ "supports_vision": true }, "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "display_name": "Claude 3.5 Sonnet v2", - "model_vendor": "anthropic", - "model_version": "20241022", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29101,9 +26044,6 @@ "supports_vision": true }, "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", - "model_version": "20250219", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29124,9 +26064,6 @@ "supports_vision": true }, "us.anthropic.claude-3-haiku-20240307-v1:0": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", - "model_version": "20240307", "input_cost_per_token": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -29141,9 +26078,6 @@ "supports_vision": true }, "us.anthropic.claude-3-opus-20240229-v1:0": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -29157,9 +26091,6 @@ "supports_vision": true }, "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "display_name": "Claude 3 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -29174,9 +26105,6 @@ "supports_vision": true }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", - "model_version": "20250805", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -29203,9 +26131,6 @@ "tool_use_system_prompt_tokens": 159 }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 4.125e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, @@ -29236,9 +26161,6 @@ "tool_use_system_prompt_tokens": 346 }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, @@ -29260,9 +26182,6 @@ "tool_use_system_prompt_tokens": 346 }, "us.anthropic.claude-opus-4-20250514-v1:0": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -29289,9 +26208,6 @@ "tool_use_system_prompt_tokens": 159 }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", - "model_version": "20251101", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -29318,9 +26234,6 @@ "tool_use_system_prompt_tokens": 159 }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", - "model_version": "20251101", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -29347,9 +26260,6 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { - "display_name": "Anthropic.claude Opus 4 5 20251101 V1:0", - "model_vendor": "anthropic", - "model_version": "0", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -29376,9 +26286,6 @@ "tool_use_system_prompt_tokens": 159 }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29409,8 +26316,6 @@ "tool_use_system_prompt_tokens": 159 }, "us.deepseek.r1-v1:0": { - "display_name": "DeepSeek R1 v1 US", - "model_vendor": "deepseek", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -29423,8 +26328,6 @@ "supports_tool_choice": false }, "us.meta.llama3-1-405b-instruct-v1:0": { - "display_name": "Llama 3.1 405B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 5.32e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29436,8 +26339,6 @@ "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { - "display_name": "Llama 3.1 70B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 9.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29449,8 +26350,6 @@ "supports_tool_choice": false }, "us.meta.llama3-1-8b-instruct-v1:0": { - "display_name": "Llama 3.1 8B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 2.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29462,8 +26361,6 @@ "supports_tool_choice": false }, "us.meta.llama3-2-11b-instruct-v1:0": { - "display_name": "Llama 3.2 11B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29476,8 +26373,6 @@ "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { - "display_name": "Llama 3.2 1B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29489,8 +26384,6 @@ "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { - "display_name": "Llama 3.2 3B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29502,8 +26395,6 @@ "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { - "display_name": "Llama 3.2 90B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -29516,8 +26407,6 @@ "supports_vision": true }, "us.meta.llama3-3-70b-instruct-v1:0": { - "display_name": "Llama 3.3 70B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -29529,8 +26418,6 @@ "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { - "display_name": "Llama 4 Maverick 17B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", @@ -29552,8 +26439,6 @@ "supports_tool_choice": false }, "us.meta.llama4-scout-17b-instruct-v1:0": { - "display_name": "Llama 4 Scout 17B Instruct v1 US", - "model_vendor": "meta", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", @@ -29575,9 +26460,6 @@ "supports_tool_choice": false }, "us.mistral.pixtral-large-2502-v1:0": { - "display_name": "Pixtral Large 2502 v1 US", - "model_vendor": "mistralai", - "model_version": "2502", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -29589,8 +26471,6 @@ "supports_tool_choice": false }, "v0/v0-1.0-md": { - "display_name": "V0 1.0 Medium", - "model_vendor": "vercel", "input_cost_per_token": 3e-06, "litellm_provider": "v0", "max_input_tokens": 128000, @@ -29605,8 +26485,6 @@ "supports_vision": true }, "v0/v0-1.5-lg": { - "display_name": "V0 1.5 Large", - "model_vendor": "vercel", "input_cost_per_token": 1.5e-05, "litellm_provider": "v0", "max_input_tokens": 512000, @@ -29621,8 +26499,6 @@ "supports_vision": true }, "v0/v0-1.5-md": { - "display_name": "V0 1.5 Medium", - "model_vendor": "vercel", "input_cost_per_token": 3e-06, "litellm_provider": "v0", "max_input_tokens": 128000, @@ -29637,8 +26513,6 @@ "supports_vision": true }, "vercel_ai_gateway/alibaba/qwen-3-14b": { - "display_name": "Qwen 3 14B", - "model_vendor": "alibaba", "input_cost_per_token": 8e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, @@ -29648,8 +26522,6 @@ "output_cost_per_token": 2.4e-07 }, "vercel_ai_gateway/alibaba/qwen-3-235b": { - "display_name": "Qwen 3 235B", - "model_vendor": "alibaba", "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, @@ -29659,8 +26531,6 @@ "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/alibaba/qwen-3-30b": { - "display_name": "Qwen 3 30B", - "model_vendor": "alibaba", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, @@ -29670,8 +26540,6 @@ "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/alibaba/qwen-3-32b": { - "display_name": "Qwen 3 32B", - "model_vendor": "alibaba", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, @@ -29681,8 +26549,6 @@ "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/alibaba/qwen3-coder": { - "display_name": "Qwen 3 Coder", - "model_vendor": "alibaba", "input_cost_per_token": 4e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, @@ -29692,8 +26558,6 @@ "output_cost_per_token": 1.6e-06 }, "vercel_ai_gateway/amazon/nova-lite": { - "display_name": "Amazon Nova Lite", - "model_vendor": "amazon", "input_cost_per_token": 6e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, @@ -29703,8 +26567,6 @@ "output_cost_per_token": 2.4e-07 }, "vercel_ai_gateway/amazon/nova-micro": { - "display_name": "Amazon Nova Micro", - "model_vendor": "amazon", "input_cost_per_token": 3.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -29714,8 +26576,6 @@ "output_cost_per_token": 1.4e-07 }, "vercel_ai_gateway/amazon/nova-pro": { - "display_name": "Amazon Nova Pro", - "model_vendor": "amazon", "input_cost_per_token": 8e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, @@ -29725,8 +26585,6 @@ "output_cost_per_token": 3.2e-06 }, "vercel_ai_gateway/amazon/titan-embed-text-v2": { - "display_name": "Amazon Titan Embed Text v2", - "model_vendor": "amazon", "input_cost_per_token": 2e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -29736,8 +26594,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/anthropic/claude-3-haiku": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3e-07, "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 2.5e-07, @@ -29749,8 +26605,6 @@ "output_cost_per_token": 1.25e-06 }, "vercel_ai_gateway/anthropic/claude-3-opus": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -29762,8 +26616,6 @@ "output_cost_per_token": 7.5e-05 }, "vercel_ai_gateway/anthropic/claude-3.5-haiku": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, @@ -29775,8 +26627,6 @@ "output_cost_per_token": 4e-06 }, "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29788,8 +26638,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29801,8 +26649,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/anthropic/claude-4-opus": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -29814,8 +26660,6 @@ "output_cost_per_token": 7.5e-05 }, "vercel_ai_gateway/anthropic/claude-4-sonnet": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -29827,8 +26671,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/cohere/command-a": { - "display_name": "Command A", - "model_vendor": "cohere", "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, @@ -29838,8 +26680,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/cohere/command-r": { - "display_name": "Command R", - "model_vendor": "cohere", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -29849,8 +26689,6 @@ "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/cohere/command-r-plus": { - "display_name": "Command R Plus", - "model_vendor": "cohere", "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -29860,8 +26698,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/cohere/embed-v4.0": { - "display_name": "Embed v4.0", - "model_vendor": "cohere", "input_cost_per_token": 1.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -29871,8 +26707,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/deepseek/deepseek-r1": { - "display_name": "DeepSeek R1", - "model_vendor": "deepseek", "input_cost_per_token": 5.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -29882,8 +26716,6 @@ "output_cost_per_token": 2.19e-06 }, "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { - "display_name": "DeepSeek R1 Distill Llama 70B", - "model_vendor": "deepseek", "input_cost_per_token": 7.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -29893,8 +26725,6 @@ "output_cost_per_token": 9.9e-07 }, "vercel_ai_gateway/deepseek/deepseek-v3": { - "display_name": "DeepSeek V3", - "model_vendor": "deepseek", "input_cost_per_token": 9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -29904,8 +26734,6 @@ "output_cost_per_token": 9e-07 }, "vercel_ai_gateway/google/gemini-2.0-flash": { - "display_name": "Gemini 2.0 Flash", - "model_vendor": "google", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -29915,8 +26743,6 @@ "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "display_name": "Gemini 2.0 Flash Lite", - "model_vendor": "google", "input_cost_per_token": 7.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -29926,8 +26752,6 @@ "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/google/gemini-2.5-flash": { - "display_name": "Gemini 2.5 Flash", - "model_vendor": "google", "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, @@ -29937,8 +26761,6 @@ "output_cost_per_token": 2.5e-06 }, "vercel_ai_gateway/google/gemini-2.5-pro": { - "display_name": "Gemini 2.5 Pro", - "model_vendor": "google", "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -29948,9 +26770,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/google/gemini-embedding-001": { - "display_name": "Gemini Embedding 001", - "model_vendor": "google", - "model_version": "001", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -29960,8 +26779,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/google/gemma-2-9b": { - "display_name": "Gemma 2 9B", - "model_vendor": "google", "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, @@ -29971,9 +26788,6 @@ "output_cost_per_token": 2e-07 }, "vercel_ai_gateway/google/text-embedding-005": { - "display_name": "Text Embedding 005", - "model_vendor": "google", - "model_version": "005", "input_cost_per_token": 2.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -29983,9 +26797,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/google/text-multilingual-embedding-002": { - "display_name": "Text Multilingual Embedding 002", - "model_vendor": "google", - "model_version": "002", "input_cost_per_token": 2.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -29995,8 +26806,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/inception/mercury-coder-small": { - "display_name": "Mercury Coder Small", - "model_vendor": "inception", "input_cost_per_token": 2.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, @@ -30006,8 +26815,6 @@ "output_cost_per_token": 1e-06 }, "vercel_ai_gateway/meta/llama-3-70b": { - "display_name": "Llama 3 70B", - "model_vendor": "meta", "input_cost_per_token": 5.9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, @@ -30017,8 +26824,6 @@ "output_cost_per_token": 7.9e-07 }, "vercel_ai_gateway/meta/llama-3-8b": { - "display_name": "Llama 3 8B", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, @@ -30028,8 +26833,6 @@ "output_cost_per_token": 8e-08 }, "vercel_ai_gateway/meta/llama-3.1-70b": { - "display_name": "Llama 3.1 70B", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30039,8 +26842,6 @@ "output_cost_per_token": 7.2e-07 }, "vercel_ai_gateway/meta/llama-3.1-8b": { - "display_name": "Llama 3.1 8B", - "model_vendor": "meta", "input_cost_per_token": 5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, @@ -30050,8 +26851,6 @@ "output_cost_per_token": 8e-08 }, "vercel_ai_gateway/meta/llama-3.2-11b": { - "display_name": "Llama 3.2 11B", - "model_vendor": "meta", "input_cost_per_token": 1.6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30061,8 +26860,6 @@ "output_cost_per_token": 1.6e-07 }, "vercel_ai_gateway/meta/llama-3.2-1b": { - "display_name": "Llama 3.2 1B", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30072,8 +26869,6 @@ "output_cost_per_token": 1e-07 }, "vercel_ai_gateway/meta/llama-3.2-3b": { - "display_name": "Llama 3.2 3B", - "model_vendor": "meta", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30083,8 +26878,6 @@ "output_cost_per_token": 1.5e-07 }, "vercel_ai_gateway/meta/llama-3.2-90b": { - "display_name": "Llama 3.2 90B", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30094,8 +26887,6 @@ "output_cost_per_token": 7.2e-07 }, "vercel_ai_gateway/meta/llama-3.3-70b": { - "display_name": "Llama 3.3 70B", - "model_vendor": "meta", "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30105,8 +26896,6 @@ "output_cost_per_token": 7.2e-07 }, "vercel_ai_gateway/meta/llama-4-maverick": { - "display_name": "Llama 4 Maverick", - "model_vendor": "meta", "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30116,8 +26905,6 @@ "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/meta/llama-4-scout": { - "display_name": "Llama 4 Scout", - "model_vendor": "meta", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30127,8 +26914,6 @@ "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/mistral/codestral": { - "display_name": "Codestral", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, @@ -30138,8 +26923,6 @@ "output_cost_per_token": 9e-07 }, "vercel_ai_gateway/mistral/codestral-embed": { - "display_name": "Codestral Embed", - "model_vendor": "mistralai", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -30149,8 +26932,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/mistral/devstral-small": { - "display_name": "Devstral Small", - "model_vendor": "mistralai", "input_cost_per_token": 7e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30160,8 +26941,6 @@ "output_cost_per_token": 2.8e-07 }, "vercel_ai_gateway/mistral/magistral-medium": { - "display_name": "Magistral Medium", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30171,8 +26950,6 @@ "output_cost_per_token": 5e-06 }, "vercel_ai_gateway/mistral/magistral-small": { - "display_name": "Magistral Small", - "model_vendor": "mistralai", "input_cost_per_token": 5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30182,8 +26959,6 @@ "output_cost_per_token": 1.5e-06 }, "vercel_ai_gateway/mistral/ministral-3b": { - "display_name": "Ministral 3B", - "model_vendor": "mistralai", "input_cost_per_token": 4e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30193,8 +26968,6 @@ "output_cost_per_token": 4e-08 }, "vercel_ai_gateway/mistral/ministral-8b": { - "display_name": "Ministral 8B", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30204,8 +26977,6 @@ "output_cost_per_token": 1e-07 }, "vercel_ai_gateway/mistral/mistral-embed": { - "display_name": "Mistral Embed", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -30215,8 +26986,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/mistral/mistral-large": { - "display_name": "Mistral Large", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, @@ -30226,8 +26995,6 @@ "output_cost_per_token": 6e-06 }, "vercel_ai_gateway/mistral/mistral-saba-24b": { - "display_name": "Mistral Saba 24B", - "model_vendor": "mistralai", "input_cost_per_token": 7.9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, @@ -30237,8 +27004,6 @@ "output_cost_per_token": 7.9e-07 }, "vercel_ai_gateway/mistral/mistral-small": { - "display_name": "Mistral Small", - "model_vendor": "mistralai", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, @@ -30248,8 +27013,6 @@ "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { - "display_name": "Mixtral 8x22B Instruct", - "model_vendor": "mistralai", "input_cost_per_token": 1.2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, @@ -30259,8 +27022,6 @@ "output_cost_per_token": 1.2e-06 }, "vercel_ai_gateway/mistral/pixtral-12b": { - "display_name": "Pixtral 12B", - "model_vendor": "mistralai", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30270,8 +27031,6 @@ "output_cost_per_token": 1.5e-07 }, "vercel_ai_gateway/mistral/pixtral-large": { - "display_name": "Pixtral Large", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30281,9 +27040,6 @@ "output_cost_per_token": 6e-06 }, "vercel_ai_gateway/moonshotai/kimi-k2": { - "display_name": "Kimi K2", - "model_vendor": "moonshot", - "model_version": "k2", "input_cost_per_token": 5.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30293,8 +27049,6 @@ "output_cost_per_token": 2.2e-06 }, "vercel_ai_gateway/morph/morph-v3-fast": { - "display_name": "Morph v3 Fast", - "model_vendor": "morph", "input_cost_per_token": 8e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, @@ -30304,8 +27058,6 @@ "output_cost_per_token": 1.2e-06 }, "vercel_ai_gateway/morph/morph-v3-large": { - "display_name": "Morph v3 Large", - "model_vendor": "morph", "input_cost_per_token": 9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, @@ -30315,8 +27067,6 @@ "output_cost_per_token": 1.9e-06 }, "vercel_ai_gateway/openai/gpt-3.5-turbo": { - "display_name": "GPT-3.5 Turbo", - "model_vendor": "openai", "input_cost_per_token": 5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, @@ -30326,8 +27076,6 @@ "output_cost_per_token": 1.5e-06 }, "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { - "display_name": "GPT-3.5 Turbo Instruct", - "model_vendor": "openai", "input_cost_per_token": 1.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, @@ -30337,8 +27085,6 @@ "output_cost_per_token": 2e-06 }, "vercel_ai_gateway/openai/gpt-4-turbo": { - "display_name": "GPT-4 Turbo", - "model_vendor": "openai", "input_cost_per_token": 1e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30348,8 +27094,6 @@ "output_cost_per_token": 3e-05 }, "vercel_ai_gateway/openai/gpt-4.1": { - "display_name": "GPT-4.1", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, @@ -30361,8 +27105,6 @@ "output_cost_per_token": 8e-06 }, "vercel_ai_gateway/openai/gpt-4.1-mini": { - "display_name": "GPT-4.1 Mini", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, @@ -30374,8 +27116,6 @@ "output_cost_per_token": 1.6e-06 }, "vercel_ai_gateway/openai/gpt-4.1-nano": { - "display_name": "GPT-4.1 Nano", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, @@ -30387,9 +27127,6 @@ "output_cost_per_token": 4e-07 }, "vercel_ai_gateway/openai/gpt-4o": { - "display_name": "GPT-4o", - "model_vendor": "openai", - "model_version": "4o", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -30401,9 +27138,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/openai/gpt-4o-mini": { - "display_name": "GPT-4o Mini", - "model_vendor": "openai", - "model_version": "4o", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, @@ -30415,8 +27149,6 @@ "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/openai/o1": { - "display_name": "o1", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, @@ -30428,8 +27160,6 @@ "output_cost_per_token": 6e-05 }, "vercel_ai_gateway/openai/o3": { - "display_name": "o3", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, @@ -30441,8 +27171,6 @@ "output_cost_per_token": 8e-06 }, "vercel_ai_gateway/openai/o3-mini": { - "display_name": "o3 Mini", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, @@ -30454,8 +27182,6 @@ "output_cost_per_token": 4.4e-06 }, "vercel_ai_gateway/openai/o4-mini": { - "display_name": "o4 Mini", - "model_vendor": "openai", "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, @@ -30467,8 +27193,6 @@ "output_cost_per_token": 4.4e-06 }, "vercel_ai_gateway/openai/text-embedding-3-large": { - "display_name": "Text Embedding 3 Large", - "model_vendor": "openai", "input_cost_per_token": 1.3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -30478,8 +27202,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/openai/text-embedding-3-small": { - "display_name": "Text Embedding 3 Small", - "model_vendor": "openai", "input_cost_per_token": 2e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -30489,9 +27211,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/openai/text-embedding-ada-002": { - "display_name": "Text Embedding Ada 002", - "model_vendor": "openai", - "model_version": "002", "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, @@ -30501,8 +27220,6 @@ "output_cost_per_token": 0.0 }, "vercel_ai_gateway/perplexity/sonar": { - "display_name": "Sonar", - "model_vendor": "perplexity", "input_cost_per_token": 1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, @@ -30512,8 +27229,6 @@ "output_cost_per_token": 1e-06 }, "vercel_ai_gateway/perplexity/sonar-pro": { - "display_name": "Sonar Pro", - "model_vendor": "perplexity", "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, @@ -30523,8 +27238,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/perplexity/sonar-reasoning": { - "display_name": "Sonar Reasoning", - "model_vendor": "perplexity", "input_cost_per_token": 1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, @@ -30534,8 +27247,6 @@ "output_cost_per_token": 5e-06 }, "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { - "display_name": "Sonar Reasoning Pro", - "model_vendor": "perplexity", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, @@ -30545,8 +27256,6 @@ "output_cost_per_token": 8e-06 }, "vercel_ai_gateway/vercel/v0-1.0-md": { - "display_name": "V0 1.0 MD", - "model_vendor": "vercel", "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30556,8 +27265,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/vercel/v0-1.5-md": { - "display_name": "V0 1.5 MD", - "model_vendor": "vercel", "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30567,8 +27274,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/xai/grok-2": { - "display_name": "Grok 2", - "model_vendor": "xai", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30578,8 +27283,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/xai/grok-2-vision": { - "display_name": "Grok 2 Vision", - "model_vendor": "xai", "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, @@ -30589,8 +27292,6 @@ "output_cost_per_token": 1e-05 }, "vercel_ai_gateway/xai/grok-3": { - "display_name": "Grok 3", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30600,8 +27301,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/xai/grok-3-fast": { - "display_name": "Grok 3 Fast", - "model_vendor": "xai", "input_cost_per_token": 5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30611,8 +27310,6 @@ "output_cost_per_token": 2.5e-05 }, "vercel_ai_gateway/xai/grok-3-mini": { - "display_name": "Grok 3 Mini", - "model_vendor": "xai", "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30622,8 +27319,6 @@ "output_cost_per_token": 5e-07 }, "vercel_ai_gateway/xai/grok-3-mini-fast": { - "display_name": "Grok 3 Mini Fast", - "model_vendor": "xai", "input_cost_per_token": 6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30633,8 +27328,6 @@ "output_cost_per_token": 4e-06 }, "vercel_ai_gateway/xai/grok-4": { - "display_name": "Grok 4", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, @@ -30644,8 +27337,6 @@ "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/zai/glm-4.5": { - "display_name": "GLM 4.5", - "model_vendor": "zhipu", "input_cost_per_token": 6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, @@ -30655,8 +27346,6 @@ "output_cost_per_token": 2.2e-06 }, "vercel_ai_gateway/zai/glm-4.5-air": { - "display_name": "GLM 4.5 Air", - "model_vendor": "zhipu", "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, @@ -30666,8 +27355,6 @@ "output_cost_per_token": 1.1e-06 }, "vercel_ai_gateway/zai/glm-4.6": { - "display_name": "GLM 4.6", - "model_vendor": "zhipu", "litellm_provider": "vercel_ai_gateway", "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 4.5e-07, @@ -30682,9 +27369,7 @@ "supports_tool_choice": true }, "vertex_ai/chirp": { - "display_name": "Chirp", - "model_vendor": "google", - "input_cost_per_character": 3e-05, + "input_cost_per_character": 30e-06, "litellm_provider": "vertex_ai", "mode": "audio_speech", "source": "https://cloud.google.com/text-to-speech/pricing", @@ -30693,8 +27378,6 @@ ] }, "vertex_ai/claude-3-5-haiku": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30708,9 +27391,6 @@ "supports_tool_choice": true }, "vertex_ai/claude-3-5-haiku@20241022": { - "display_name": "Claude 3.5 Haiku", - "model_vendor": "anthropic", - "model_version": "20241022", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30724,9 +27404,6 @@ "supports_tool_choice": true }, "vertex_ai/claude-haiku-4-5@20251001": { - "display_name": "Claude Haiku 4.5", - "model_vendor": "anthropic", - "model_version": "20251001", "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, @@ -30746,8 +27423,6 @@ "supports_tool_choice": true }, "vertex_ai/claude-3-5-sonnet": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30763,8 +27438,6 @@ "supports_vision": true }, "vertex_ai/claude-3-5-sonnet-v2": { - "display_name": "Claude 3.5 Sonnet v2", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30780,9 +27453,6 @@ "supports_vision": true }, "vertex_ai/claude-3-5-sonnet-v2@20241022": { - "display_name": "Claude 3.5 Sonnet v2", - "model_vendor": "anthropic", - "model_version": "20241022", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30798,9 +27468,6 @@ "supports_vision": true }, "vertex_ai/claude-3-5-sonnet@20240620": { - "display_name": "Claude 3.5 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240620", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30815,9 +27482,6 @@ "supports_vision": true }, "vertex_ai/claude-3-7-sonnet@20250219": { - "display_name": "Claude 3.7 Sonnet", - "model_vendor": "anthropic", - "model_version": "20250219", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", @@ -30840,8 +27504,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-3-haiku": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30855,9 +27517,6 @@ "supports_vision": true }, "vertex_ai/claude-3-haiku@20240307": { - "display_name": "Claude 3 Haiku", - "model_vendor": "anthropic", - "model_version": "20240307", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30871,8 +27530,6 @@ "supports_vision": true }, "vertex_ai/claude-3-opus": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30886,9 +27543,6 @@ "supports_vision": true }, "vertex_ai/claude-3-opus@20240229": { - "display_name": "Claude 3 Opus", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30902,8 +27556,6 @@ "supports_vision": true }, "vertex_ai/claude-3-sonnet": { - "display_name": "Claude 3 Sonnet", - "model_vendor": "anthropic", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30917,9 +27569,6 @@ "supports_vision": true }, "vertex_ai/claude-3-sonnet@20240229": { - "display_name": "Claude 3 Sonnet", - "model_vendor": "anthropic", - "model_version": "20240229", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -30933,8 +27582,6 @@ "supports_vision": true }, "vertex_ai/claude-opus-4": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -30961,8 +27608,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-opus-4-1": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -30980,9 +27625,6 @@ "supports_vision": true }, "vertex_ai/claude-opus-4-1@20250805": { - "display_name": "Claude Opus 4.1", - "model_vendor": "anthropic", - "model_version": "20250805", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -31000,8 +27642,6 @@ "supports_vision": true }, "vertex_ai/claude-opus-4-5": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -31028,9 +27668,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-opus-4-5@20251101": { - "display_name": "Claude Opus 4.5", - "model_vendor": "anthropic", - "model_version": "20251101", "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -31057,8 +27694,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-sonnet-4-5": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -31085,9 +27720,6 @@ "supports_vision": true }, "vertex_ai/claude-sonnet-4-5@20250929": { - "display_name": "Claude Sonnet 4.5", - "model_vendor": "anthropic", - "model_version": "20250929", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -31114,9 +27746,6 @@ "supports_vision": true }, "vertex_ai/claude-opus-4@20250514": { - "display_name": "Claude Opus 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, @@ -31143,8 +27772,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-sonnet-4": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -31175,9 +27802,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/claude-sonnet-4@20250514": { - "display_name": "Claude Sonnet 4", - "model_vendor": "anthropic", - "model_version": "20250514", "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -31208,8 +27832,6 @@ "tool_use_system_prompt_tokens": 159 }, "vertex_ai/mistralai/codestral-2@001": { - "display_name": "Codestral 2", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31221,8 +27843,6 @@ "supports_tool_choice": true }, "vertex_ai/codestral-2": { - "display_name": "Codestral 2", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31234,8 +27854,6 @@ "supports_tool_choice": true }, "vertex_ai/codestral-2@001": { - "display_name": "Codestral 2 @001", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31247,8 +27865,6 @@ "supports_tool_choice": true }, "vertex_ai/mistralai/codestral-2": { - "display_name": "Codestral 2", - "model_vendor": "mistralai", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31260,8 +27876,6 @@ "supports_tool_choice": true }, "vertex_ai/codestral-2501": { - "display_name": "Codestral 2501", - "model_vendor": "mistralai", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31273,8 +27887,6 @@ "supports_tool_choice": true }, "vertex_ai/codestral@2405": { - "display_name": "Codestral 2405", - "model_vendor": "mistralai", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31286,8 +27898,6 @@ "supports_tool_choice": true }, "vertex_ai/codestral@latest": { - "display_name": "Codestral Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31299,8 +27909,6 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "display_name": "DeepSeek V3.1 MaaS", - "model_vendor": "deepseek", "input_cost_per_token": 1.35e-06, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, @@ -31319,9 +27927,6 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { - "display_name": "Deepseek AI Deepseek V3.2 Maas", - "model_vendor": "deepseek", - "model_version": "3.2", "input_cost_per_token": 5.6e-07, "input_cost_per_token_batches": 2.8e-07, "litellm_provider": "vertex_ai-deepseek_models", @@ -31342,8 +27947,6 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { - "display_name": "DeepSeek R1 0528 MaaS", - "model_vendor": "deepseek", "input_cost_per_token": 1.35e-06, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, @@ -31359,8 +27962,6 @@ "supports_tool_choice": true }, "vertex_ai/gemini-2.5-flash-image": { - "display_name": "Gemini 2.5 Flash Image", - "model_vendor": "google", "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -31376,6 +27977,7 @@ "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, @@ -31409,8 +28011,6 @@ "tpm": 8000000 }, "vertex_ai/gemini-3-pro-image-preview": { - "display_name": "Gemini 3 Pro Image Preview", - "model_vendor": "google", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -31420,78 +28020,61 @@ "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token": 1.2e-04, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "vertex_ai/imagegeneration@006": { - "display_name": "Image Generation 006", - "model_vendor": "google", "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": { - "display_name": "Imagen 3.0 Fast Generate 001", - "model_vendor": "google", "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": { - "display_name": "Imagen 3.0 Generate 001", - "model_vendor": "google", "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": { - "display_name": "Imagen 3.0 Generate 002", - "model_vendor": "google", + "deprecation_date": "2025-11-10", "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-capability-001": { - "display_name": "Imagen 3.0 Capability 001", - "model_vendor": "google", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" }, "vertex_ai/imagen-4.0-fast-generate-001": { - "display_name": "Imagen 4.0 Fast Generate 001", - "model_vendor": "google", "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": { - "display_name": "Imagen 4.0 Generate 001", - "model_vendor": "google", "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": { - "display_name": "Imagen 4.0 Ultra Generate 001", - "model_vendor": "google", "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": { - "display_name": "Jamba 1.5", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -31502,8 +28085,6 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large": { - "display_name": "Jamba 1.5 Large", - "model_vendor": "ai21", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -31514,8 +28095,6 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large@001": { - "display_name": "Jamba 1.5 Large @001", - "model_vendor": "ai21", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -31526,8 +28105,6 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini": { - "display_name": "Jamba 1.5 Mini", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -31538,8 +28115,6 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini@001": { - "display_name": "Jamba 1.5 Mini @001", - "model_vendor": "ai21", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -31550,8 +28125,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama-3.1-405b-instruct-maas": { - "display_name": "Llama 3.1 405B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, @@ -31565,8 +28138,6 @@ "supports_vision": true }, "vertex_ai/meta/llama-3.1-70b-instruct-maas": { - "display_name": "Llama 3.1 70B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, @@ -31580,8 +28151,6 @@ "supports_vision": true }, "vertex_ai/meta/llama-3.1-8b-instruct-maas": { - "display_name": "Llama 3.1 8B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, @@ -31598,8 +28167,6 @@ "supports_vision": true }, "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { - "display_name": "Llama 3.2 90B Vision Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, @@ -31616,8 +28183,6 @@ "supports_vision": true }, "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { - "display_name": "Llama 4 Maverick 17B 128E Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 3.5e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, @@ -31638,8 +28203,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { - "display_name": "Llama 4 Maverick 17B 16E Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 3.5e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, @@ -31660,8 +28223,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { - "display_name": "Llama 4 Scout 17B 128E Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, @@ -31682,8 +28243,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { - "display_name": "Llama 4 Scout 17B 16E Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, @@ -31704,8 +28263,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama3-405b-instruct-maas": { - "display_name": "Llama 3 405B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, @@ -31717,8 +28274,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama3-70b-instruct-maas": { - "display_name": "Llama 3 70B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, @@ -31730,8 +28285,6 @@ "supports_tool_choice": true }, "vertex_ai/meta/llama3-8b-instruct-maas": { - "display_name": "Llama 3 8B Instruct MaaS", - "model_vendor": "meta", "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, @@ -31743,8 +28296,6 @@ "supports_tool_choice": true }, "vertex_ai/minimaxai/minimax-m2-maas": { - "display_name": "MiniMax M2 MaaS", - "model_vendor": "minimax", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, @@ -31757,8 +28308,6 @@ "supports_tool_choice": true }, "vertex_ai/moonshotai/kimi-k2-thinking-maas": { - "display_name": "Kimi K2 Thinking MaaS", - "model_vendor": "moonshot", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, @@ -31772,8 +28321,6 @@ "supports_web_search": true }, "vertex_ai/mistral-medium-3": { - "display_name": "Mistral Medium 3", - "model_vendor": "mistralai", "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31785,8 +28332,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-medium-3@001": { - "display_name": "Mistral Medium 3 @001", - "model_vendor": "mistralai", "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31798,8 +28343,6 @@ "supports_tool_choice": true }, "vertex_ai/mistralai/mistral-medium-3": { - "display_name": "Mistral Medium 3", - "model_vendor": "mistralai", "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31811,8 +28354,6 @@ "supports_tool_choice": true }, "vertex_ai/mistralai/mistral-medium-3@001": { - "display_name": "Mistral Medium 3 @001", - "model_vendor": "mistralai", "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31824,8 +28365,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-large-2411": { - "display_name": "Mistral Large 2411", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31837,8 +28376,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-large@2407": { - "display_name": "Mistral Large 2407", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31850,8 +28387,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-large@2411-001": { - "display_name": "Mistral Large 2411-001", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31863,8 +28398,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-large@latest": { - "display_name": "Mistral Large Latest", - "model_vendor": "mistralai", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31876,8 +28409,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-nemo@2407": { - "display_name": "Mistral Nemo 2407", - "model_vendor": "mistralai", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31889,8 +28420,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-nemo@latest": { - "display_name": "Mistral Nemo Latest", - "model_vendor": "mistralai", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31902,8 +28431,6 @@ "supports_tool_choice": true }, "vertex_ai/mistral-small-2503": { - "display_name": "Mistral Small 2503", - "model_vendor": "mistralai", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, @@ -31916,8 +28443,6 @@ "supports_vision": true }, "vertex_ai/mistral-small-2503@001": { - "display_name": "Mistral Small 2503 @001", - "model_vendor": "mistralai", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, @@ -31929,19 +28454,23 @@ "supports_tool_choice": true }, "vertex_ai/mistral-ocr-2505": { - "display_name": "Mistral OCR 2505", - "model_vendor": "mistralai", "litellm_provider": "vertex_ai", "mode": "ocr", - "ocr_cost_per_page": 0.0005, + "ocr_cost_per_page": 5e-4, "supported_endpoints": [ "/v1/ocr" ], "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, + "vertex_ai/deepseek-ai/deepseek-ocr-maas": { + "litellm_provider": "vertex_ai", + "mode": "ocr", + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "ocr_cost_per_page": 3e-04, + "source": "https://cloud.google.com/vertex-ai/pricing" + }, "vertex_ai/openai/gpt-oss-120b-maas": { - "display_name": "GPT-OSS 120B MaaS", - "model_vendor": "openai", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, @@ -31953,8 +28482,6 @@ "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { - "display_name": "GPT-OSS 20B MaaS", - "model_vendor": "openai", "input_cost_per_token": 7.5e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, @@ -31966,8 +28493,6 @@ "supports_reasoning": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "display_name": "Qwen 3 235B A22B Instruct 2507 MaaS", - "model_vendor": "alibaba", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -31980,8 +28505,6 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "display_name": "Qwen 3 Coder 480B A35B Instruct MaaS", - "model_vendor": "alibaba", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -31994,8 +28517,6 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { - "display_name": "Qwen 3 Next 80B A3B Instruct MaaS", - "model_vendor": "alibaba", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -32008,8 +28529,6 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { - "display_name": "Qwen 3 Next 80B A3B Thinking MaaS", - "model_vendor": "alibaba", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -32022,8 +28541,6 @@ "supports_tool_choice": true }, "vertex_ai/veo-2.0-generate-001": { - "display_name": "Veo 2.0 Generate 001", - "model_vendor": "google", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32038,8 +28555,7 @@ ] }, "vertex_ai/veo-3.0-fast-generate-preview": { - "display_name": "Veo 3.0 Fast Generate Preview", - "model_vendor": "google", + "deprecation_date": "2025-11-12", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32054,8 +28570,7 @@ ] }, "vertex_ai/veo-3.0-generate-preview": { - "display_name": "Veo 3.0 Generate Preview", - "model_vendor": "google", + "deprecation_date": "2025-11-12", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32070,8 +28585,6 @@ ] }, "vertex_ai/veo-3.0-fast-generate-001": { - "display_name": "Veo 3.0 Fast Generate 001", - "model_vendor": "google", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32086,8 +28599,6 @@ ] }, "vertex_ai/veo-3.0-generate-001": { - "display_name": "Veo 3.0 Generate 001", - "model_vendor": "google", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32102,8 +28613,6 @@ ] }, "vertex_ai/veo-3.1-generate-preview": { - "display_name": "Veo 3.1 Generate Preview", - "model_vendor": "google", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32118,8 +28627,34 @@ ] }, "vertex_ai/veo-3.1-fast-generate-preview": { - "display_name": "Veo 3.1 Fast Generate Preview", - "model_vendor": "google", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.1-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.1-fast-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, @@ -32134,8 +28669,6 @@ ] }, "voyage/rerank-2": { - "display_name": "Rerank 2", - "model_vendor": "voyage", "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 16000, @@ -32146,8 +28679,6 @@ "output_cost_per_token": 0.0 }, "voyage/rerank-2-lite": { - "display_name": "Rerank 2 Lite", - "model_vendor": "voyage", "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 8000, @@ -32158,9 +28689,6 @@ "output_cost_per_token": 0.0 }, "voyage/rerank-2.5": { - "display_name": "Rerank 2.5", - "model_vendor": "voyage", - "model_version": "2.5", "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32171,9 +28699,6 @@ "output_cost_per_token": 0.0 }, "voyage/rerank-2.5-lite": { - "display_name": "Rerank 2.5 Lite", - "model_vendor": "voyage", - "model_version": "2.5", "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32184,8 +28709,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-2": { - "display_name": "Voyage 2", - "model_vendor": "voyage", "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, @@ -32194,8 +28717,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-3": { - "display_name": "Voyage 3", - "model_vendor": "voyage", "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32204,8 +28725,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-3-large": { - "display_name": "Voyage 3 Large", - "model_vendor": "voyage", "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32214,8 +28733,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-3-lite": { - "display_name": "Voyage 3 Lite", - "model_vendor": "voyage", "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32224,8 +28741,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-3.5": { - "display_name": "Voyage 3.5", - "model_vendor": "voyage", "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32234,8 +28749,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-3.5-lite": { - "display_name": "Voyage 3.5 Lite", - "model_vendor": "voyage", "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32244,8 +28757,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-code-2": { - "display_name": "Voyage Code 2", - "model_vendor": "voyage", "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, @@ -32254,8 +28765,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-code-3": { - "display_name": "Voyage Code 3", - "model_vendor": "voyage", "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32264,8 +28773,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-context-3": { - "display_name": "Voyage Context 3", - "model_vendor": "voyage", "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, @@ -32274,8 +28781,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-finance-2": { - "display_name": "Voyage Finance 2", - "model_vendor": "voyage", "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32284,8 +28789,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-large-2": { - "display_name": "Voyage Large 2", - "model_vendor": "voyage", "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, @@ -32294,8 +28797,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-law-2": { - "display_name": "Voyage Law 2", - "model_vendor": "voyage", "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, @@ -32304,8 +28805,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-lite-01": { - "display_name": "Voyage Lite 01", - "model_vendor": "voyage", "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4096, @@ -32314,8 +28813,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-lite-02-instruct": { - "display_name": "Voyage Lite 02 Instruct", - "model_vendor": "voyage", "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, @@ -32324,8 +28821,6 @@ "output_cost_per_token": 0.0 }, "voyage/voyage-multimodal-3": { - "display_name": "Voyage Multimodal 3", - "model_vendor": "voyage", "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, @@ -32334,8 +28829,6 @@ "output_cost_per_token": 0.0 }, "wandb/openai/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -32345,8 +28838,6 @@ "mode": "chat" }, "wandb/openai/gpt-oss-20b": { - "display_name": "GPT-OSS 20B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -32356,8 +28847,6 @@ "mode": "chat" }, "wandb/zai-org/GLM-4.5": { - "display_name": "GLM 4.5", - "model_vendor": "zhipu", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -32367,8 +28856,6 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "display_name": "Qwen 3 235B A22B Instruct 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -32378,8 +28865,6 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "display_name": "Qwen 3 Coder 480B A35B Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -32389,8 +28874,6 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "display_name": "Qwen 3 235B A22B Thinking 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -32400,8 +28883,6 @@ "mode": "chat" }, "wandb/moonshotai/Kimi-K2-Instruct": { - "display_name": "Kimi K2 Instruct", - "model_vendor": "moonshot", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32411,8 +28892,6 @@ "mode": "chat" }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "display_name": "Llama 3.1 8B Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32422,8 +28901,6 @@ "mode": "chat" }, "wandb/deepseek-ai/DeepSeek-V3.1": { - "display_name": "DeepSeek V3.1", - "model_vendor": "deepseek", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32433,8 +28910,6 @@ "mode": "chat" }, "wandb/deepseek-ai/DeepSeek-R1-0528": { - "display_name": "DeepSeek R1 0528", - "model_vendor": "deepseek", "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, @@ -32444,8 +28919,6 @@ "mode": "chat" }, "wandb/deepseek-ai/DeepSeek-V3-0324": { - "display_name": "DeepSeek V3 0324", - "model_vendor": "deepseek", "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, @@ -32455,8 +28928,6 @@ "mode": "chat" }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32466,8 +28937,6 @@ "mode": "chat" }, "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "display_name": "Llama 4 Scout 17B 16E Instruct", - "model_vendor": "meta", "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, @@ -32477,8 +28946,6 @@ "mode": "chat" }, "wandb/microsoft/Phi-4-mini-instruct": { - "display_name": "Phi 4 Mini Instruct", - "model_vendor": "microsoft", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32488,15 +28955,13 @@ "mode": "chat" }, "watsonx/ibm/granite-3-8b-instruct": { - "display_name": "Granite 3 8B Instruct", - "model_vendor": "ibm", - "input_cost_per_token": 2e-07, + "input_cost_per_token": 0.2e-06, "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 0.2e-06, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, @@ -32508,15 +28973,13 @@ "supports_vision": false }, "watsonx/mistralai/mistral-large": { - "display_name": "Mistral Large", - "model_vendor": "mistralai", "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, + "output_cost_per_token": 10e-06, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, @@ -32528,8 +28991,6 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "display_name": "MT0 XXL 13B", - "model_vendor": "bigscience", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -32542,8 +29003,6 @@ "supports_vision": false }, "watsonx/core42/jais-13b-chat": { - "display_name": "JAIS 13B Chat", - "model_vendor": "core42", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -32556,13 +29015,11 @@ "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { - "display_name": "Flan T5 XL 3B", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 0.6e-06, + "output_cost_per_token": 0.6e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32570,13 +29027,11 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { - "display_name": "Granite 13B Chat V2", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 0.6e-06, + "output_cost_per_token": 0.6e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32584,13 +29039,11 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { - "display_name": "Granite 13B Instruct V2", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 0.6e-06, + "output_cost_per_token": 0.6e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32598,13 +29051,11 @@ "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { - "display_name": "Granite 3.3 8B Instruct", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, + "input_cost_per_token": 0.2e-06, + "output_cost_per_token": 0.2e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32612,13 +29063,11 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "display_name": "Granite 4 H Small", - "model_vendor": "ibm", "max_tokens": 20480, "max_input_tokens": 20480, "max_output_tokens": 20480, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.5e-07, + "input_cost_per_token": 0.06e-06, + "output_cost_per_token": 0.25e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32626,13 +29075,11 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-2-2b": { - "display_name": "Granite Guardian 3.2 2B", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, + "input_cost_per_token": 0.1e-06, + "output_cost_per_token": 0.1e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32640,13 +29087,11 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { - "display_name": "Granite Guardian 3.3 8B", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, + "input_cost_per_token": 0.2e-06, + "output_cost_per_token": 0.2e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32654,13 +29099,11 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { - "display_name": "Granite TTM 1024 96 R2", - "model_vendor": "ibm", "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, - "input_cost_per_token": 3.8e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 0.38e-06, + "output_cost_per_token": 0.38e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32668,13 +29111,11 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { - "display_name": "Granite TTM 1536 96 R2", - "model_vendor": "ibm", "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, - "input_cost_per_token": 3.8e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 0.38e-06, + "output_cost_per_token": 0.38e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32682,13 +29123,11 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { - "display_name": "Granite TTM 512 96 R2", - "model_vendor": "ibm", "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, - "input_cost_per_token": 3.8e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 0.38e-06, + "output_cost_per_token": 0.38e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32696,13 +29135,11 @@ "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { - "display_name": "Granite Vision 3.2 2B", - "model_vendor": "ibm", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, + "input_cost_per_token": 0.1e-06, + "output_cost_per_token": 0.1e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32710,13 +29147,11 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "display_name": "Llama 3.2 11B Vision Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, + "input_cost_per_token": 0.35e-06, + "output_cost_per_token": 0.35e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32724,13 +29159,11 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { - "display_name": "Llama 3.2 1B Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, + "input_cost_per_token": 0.1e-06, + "output_cost_per_token": 0.1e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32738,13 +29171,11 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { - "display_name": "Llama 3.2 3B Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, + "input_cost_per_token": 0.15e-06, + "output_cost_per_token": 0.15e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32752,8 +29183,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "display_name": "Llama 3.2 90B Vision Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -32766,13 +29195,11 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "display_name": "Llama 3.3 70B Instruct", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 7.1e-07, + "input_cost_per_token": 0.71e-06, + "output_cost_per_token": 0.71e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32780,12 +29207,10 @@ "supports_vision": false }, "watsonx/meta-llama/llama-4-maverick-17b": { - "display_name": "Llama 4 Maverick 17B", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, + "input_cost_per_token": 0.35e-06, "output_cost_per_token": 1.4e-06, "litellm_provider": "watsonx", "mode": "chat", @@ -32794,13 +29219,11 @@ "supports_vision": false }, "watsonx/meta-llama/llama-guard-3-11b-vision": { - "display_name": "Llama Guard 3 11B Vision", - "model_vendor": "meta", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, + "input_cost_per_token": 0.35e-06, + "output_cost_per_token": 0.35e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32808,13 +29231,11 @@ "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { - "display_name": "Mistral Medium 2505", - "model_vendor": "mistralai", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, - "output_cost_per_token": 1e-05, + "output_cost_per_token": 10e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32822,13 +29243,11 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { - "display_name": "Mistral Small 2503", - "model_vendor": "mistralai", "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 0.1e-06, + "output_cost_per_token": 0.3e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32836,13 +29255,11 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "display_name": "Mistral Small 3.1 24B Instruct 2503", - "model_vendor": "mistralai", "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 0.1e-06, + "output_cost_per_token": 0.3e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, @@ -32850,13 +29267,11 @@ "supports_vision": false }, "watsonx/mistralai/pixtral-12b-2409": { - "display_name": "Pixtral 12B 2409", - "model_vendor": "mistralai", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, + "input_cost_per_token": 0.35e-06, + "output_cost_per_token": 0.35e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32864,13 +29279,11 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "display_name": "GPT-OSS 120B", - "model_vendor": "openai", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 0.15e-06, + "output_cost_per_token": 0.6e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -32878,8 +29291,6 @@ "supports_vision": false }, "watsonx/sdaia/allam-1-13b-instruct": { - "display_name": "ALLaM 1 13B Instruct", - "model_vendor": "sdaia", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -32892,8 +29303,6 @@ "supports_vision": false }, "watsonx/whisper-large-v3-turbo": { - "display_name": "Whisper Large v3 Turbo", - "model_vendor": "openai", "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "litellm_provider": "watsonx", @@ -32903,8 +29312,6 @@ ] }, "whisper-1": { - "display_name": "Whisper 1", - "model_vendor": "openai", "input_cost_per_second": 0.0001, "litellm_provider": "openai", "mode": "audio_transcription", @@ -32914,8 +29321,6 @@ ] }, "xai/grok-2": { - "display_name": "Grok 2", - "model_vendor": "xai", "input_cost_per_token": 2e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -32928,8 +29333,6 @@ "supports_web_search": true }, "xai/grok-2-1212": { - "display_name": "Grok 2 1212", - "model_vendor": "xai", "input_cost_per_token": 2e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -32942,8 +29345,6 @@ "supports_web_search": true }, "xai/grok-2-latest": { - "display_name": "Grok 2 Latest", - "model_vendor": "xai", "input_cost_per_token": 2e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -32956,8 +29357,6 @@ "supports_web_search": true }, "xai/grok-2-vision": { - "display_name": "Grok 2 Vision", - "model_vendor": "xai", "input_cost_per_image": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "xai", @@ -32972,8 +29371,6 @@ "supports_web_search": true }, "xai/grok-2-vision-1212": { - "display_name": "Grok 2 Vision 1212", - "model_vendor": "xai", "input_cost_per_image": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "xai", @@ -32988,8 +29385,6 @@ "supports_web_search": true }, "xai/grok-2-vision-latest": { - "display_name": "Grok 2 Vision Latest", - "model_vendor": "xai", "input_cost_per_image": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "xai", @@ -33004,8 +29399,6 @@ "supports_web_search": true }, "xai/grok-3": { - "display_name": "Grok 3", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33020,8 +29413,6 @@ "supports_web_search": true }, "xai/grok-3-beta": { - "display_name": "Grok 3 Beta", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33036,8 +29427,6 @@ "supports_web_search": true }, "xai/grok-3-fast-beta": { - "display_name": "Grok 3 Fast Beta", - "model_vendor": "xai", "input_cost_per_token": 5e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33052,8 +29441,6 @@ "supports_web_search": true }, "xai/grok-3-fast-latest": { - "display_name": "Grok 3 Fast Latest", - "model_vendor": "xai", "input_cost_per_token": 5e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33068,8 +29455,6 @@ "supports_web_search": true }, "xai/grok-3-latest": { - "display_name": "Grok 3 Latest", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33084,8 +29469,6 @@ "supports_web_search": true }, "xai/grok-3-mini": { - "display_name": "Grok 3 Mini", - "model_vendor": "xai", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33101,8 +29484,6 @@ "supports_web_search": true }, "xai/grok-3-mini-beta": { - "display_name": "Grok 3 Mini Beta", - "model_vendor": "xai", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33118,8 +29499,6 @@ "supports_web_search": true }, "xai/grok-3-mini-fast": { - "display_name": "Grok 3 Mini Fast", - "model_vendor": "xai", "input_cost_per_token": 6e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33135,8 +29514,6 @@ "supports_web_search": true }, "xai/grok-3-mini-fast-beta": { - "display_name": "Grok 3 Mini Fast Beta", - "model_vendor": "xai", "input_cost_per_token": 6e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33152,8 +29529,6 @@ "supports_web_search": true }, "xai/grok-3-mini-fast-latest": { - "display_name": "Grok 3 Mini Fast Latest", - "model_vendor": "xai", "input_cost_per_token": 6e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33169,8 +29544,6 @@ "supports_web_search": true }, "xai/grok-3-mini-latest": { - "display_name": "Grok 3 Mini Latest", - "model_vendor": "xai", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33186,8 +29559,6 @@ "supports_web_search": true }, "xai/grok-4": { - "display_name": "Grok 4", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "litellm_provider": "xai", "max_input_tokens": 256000, @@ -33201,35 +29572,31 @@ "supports_web_search": true }, "xai/grok-4-fast-reasoning": { - "display_name": "Grok 4 Fast Reasoning", - "model_vendor": "xai", "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "output_cost_per_token": 5e-07, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, - "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost": 0.05e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "xai/grok-4-fast-non-reasoning": { - "display_name": "Grok 4 Fast Non-Reasoning", - "model_vendor": "xai", "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "cache_read_input_token_cost": 5e-08, - "max_tokens": 2000000.0, + "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": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "output_cost_per_token": 5e-07, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, @@ -33237,8 +29604,6 @@ "supports_web_search": true }, "xai/grok-4-0709": { - "display_name": "Grok 4 0709", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "input_cost_per_token_above_128k_tokens": 6e-06, "litellm_provider": "xai", @@ -33247,15 +29612,13 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_128k_tokens": 3e-05, + "output_cost_per_token_above_128k_tokens": 30e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "xai/grok-4-latest": { - "display_name": "Grok 4 Latest", - "model_vendor": "xai", "input_cost_per_token": 3e-06, "input_cost_per_token_above_128k_tokens": 6e-06, "litellm_provider": "xai", @@ -33264,24 +29627,22 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_128k_tokens": 3e-05, + "output_cost_per_token_above_128k_tokens": 30e-06, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "xai/grok-4-1-fast": { - "display_name": "Grok 4.1 Fast", - "model_vendor": "xai", - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, @@ -33293,17 +29654,15 @@ "supports_web_search": true }, "xai/grok-4-1-fast-reasoning": { - "display_name": "Grok 4.1 Fast Reasoning", - "model_vendor": "xai", - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, @@ -33315,17 +29674,15 @@ "supports_web_search": true }, "xai/grok-4-1-fast-reasoning-latest": { - "display_name": "Grok 4.1 Fast Reasoning Latest", - "model_vendor": "xai", - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, @@ -33337,17 +29694,15 @@ "supports_web_search": true }, "xai/grok-4-1-fast-non-reasoning": { - "display_name": "Grok 4.1 Fast Non-Reasoning", - "model_vendor": "xai", - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, @@ -33358,17 +29713,15 @@ "supports_web_search": true }, "xai/grok-4-1-fast-non-reasoning-latest": { - "display_name": "Grok 4.1 Fast Non-Reasoning Latest", - "model_vendor": "xai", - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 0.5e-06, "output_cost_per_token_above_128k_tokens": 1e-06, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, @@ -33379,8 +29732,6 @@ "supports_web_search": true }, "xai/grok-beta": { - "display_name": "Grok Beta", - "model_vendor": "xai", "input_cost_per_token": 5e-06, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33394,8 +29745,6 @@ "supports_web_search": true }, "xai/grok-code-fast": { - "display_name": "Grok Code Fast", - "model_vendor": "xai", "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "xai", @@ -33410,8 +29759,6 @@ "supports_tool_choice": true }, "xai/grok-code-fast-1": { - "display_name": "Grok Code Fast 1", - "model_vendor": "xai", "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "xai", @@ -33426,8 +29773,6 @@ "supports_tool_choice": true }, "xai/grok-code-fast-1-0825": { - "display_name": "Grok Code Fast 1 0825", - "model_vendor": "xai", "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "xai", @@ -33442,8 +29787,6 @@ "supports_tool_choice": true }, "xai/grok-vision-beta": { - "display_name": "Grok Vision Beta", - "model_vendor": "xai", "input_cost_per_image": 5e-06, "input_cost_per_token": 5e-06, "litellm_provider": "xai", @@ -33457,9 +29800,21 @@ "supports_vision": true, "supports_web_search": true }, + "zai/glm-4.7": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.2e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, "zai/glm-4.6": { - "display_name": "GLM-4.6", - "model_vendor": "zhipu", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "zai", @@ -33471,8 +29826,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5": { - "display_name": "GLM-4.5", - "model_vendor": "zhipu", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "zai", @@ -33484,8 +29837,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5v": { - "display_name": "GLM-4.5V", - "model_vendor": "zhipu", "input_cost_per_token": 6e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "zai", @@ -33498,8 +29849,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-x": { - "display_name": "GLM-4.5X", - "model_vendor": "zhipu", "input_cost_per_token": 2.2e-06, "output_cost_per_token": 8.9e-06, "litellm_provider": "zai", @@ -33511,8 +29860,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-air": { - "display_name": "GLM-4.5 Air", - "model_vendor": "zhipu", "input_cost_per_token": 2e-07, "output_cost_per_token": 1.1e-06, "litellm_provider": "zai", @@ -33524,8 +29871,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-airx": { - "display_name": "GLM-4.5 AirX", - "model_vendor": "zhipu", "input_cost_per_token": 1.1e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "zai", @@ -33537,8 +29882,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4-32b-0414-128k": { - "display_name": "GLM-4 32B", - "model_vendor": "zhipu", "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "zai", @@ -33550,8 +29893,6 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-flash": { - "display_name": "GLM-4.5 Flash", - "model_vendor": "zhipu", "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "zai", @@ -33563,25 +29904,19 @@ "source": "https://docs.z.ai/guides/overview/pricing" }, "vertex_ai/search_api": { - "display_name": "Search API", - "model_vendor": "google", - "input_cost_per_query": 0.0015, + "input_cost_per_query": 1.5e-03, "litellm_provider": "vertex_ai", "mode": "vector_store" }, "openai/container": { - "display_name": "Container", - "model_vendor": "openai", "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", "mode": "chat" }, "openai/sora-2": { - "display_name": "Sora 2", - "model_vendor": "openai", "litellm_provider": "openai", "mode": "video_generation", - "output_cost_per_video_per_second": 0.1, + "output_cost_per_video_per_second": 0.10, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", @@ -33596,11 +29931,9 @@ ] }, "openai/sora-2-pro": { - "display_name": "Sora 2 Pro", - "model_vendor": "openai", "litellm_provider": "openai", "mode": "video_generation", - "output_cost_per_video_per_second": 0.3, + "output_cost_per_video_per_second": 0.30, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", @@ -33615,11 +29948,9 @@ ] }, "azure/sora-2": { - "display_name": "Sora 2", - "model_vendor": "openai", "litellm_provider": "azure", "mode": "video_generation", - "output_cost_per_video_per_second": 0.1, + "output_cost_per_video_per_second": 0.10, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" @@ -33633,11 +29964,9 @@ ] }, "azure/sora-2-pro": { - "display_name": "Sora 2 Pro", - "model_vendor": "openai", "litellm_provider": "azure", "mode": "video_generation", - "output_cost_per_video_per_second": 0.3, + "output_cost_per_video_per_second": 0.30, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" @@ -33651,11 +29980,9 @@ ] }, "azure/sora-2-pro-high-res": { - "display_name": "Sora 2 Pro High Res", - "model_vendor": "openai", "litellm_provider": "azure", "mode": "video_generation", - "output_cost_per_video_per_second": 0.5, + "output_cost_per_video_per_second": 0.50, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" @@ -33669,8 +29996,6 @@ ] }, "runwayml/gen4_turbo": { - "display_name": "Gen4 Turbo", - "model_vendor": "runwayml", "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.05, @@ -33691,8 +30016,6 @@ } }, "runwayml/gen4_aleph": { - "display_name": "Gen4 Aleph", - "model_vendor": "runwayml", "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.15, @@ -33713,9 +30036,6 @@ } }, "runwayml/gen3a_turbo": { - "display_name": "Gen3a Turbo", - "model_vendor": "runwayml", - "model_version": "3a", "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.05, @@ -33736,8 +30056,6 @@ } }, "runwayml/gen4_image": { - "display_name": "Gen4 Image", - "model_vendor": "runwayml", "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.05, @@ -33759,8 +30077,6 @@ } }, "runwayml/gen4_image_turbo": { - "display_name": "Gen4 Image Turbo", - "model_vendor": "runwayml", "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.02, @@ -33782,8 +30098,6 @@ } }, "runwayml/eleven_multilingual_v2": { - "display_name": "Eleven Multilingual v2", - "model_vendor": "elevenlabs", "litellm_provider": "runwayml", "mode": "audio_speech", "input_cost_per_character": 3e-07, @@ -33793,19 +30107,16 @@ } }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "display_name": "Qwen3 Coder 480B A35b Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { - "display_name": "Flux Kontext Pro", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33815,8 +30126,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { - "display_name": "SSD 1B", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33826,8 +30135,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "display_name": "Chronos Hermes 13B V2", - "model_vendor": "nousresearch", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33837,8 +30144,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "display_name": "Code Llama 13B", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33848,8 +30153,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "display_name": "Code Llama 13B Instruct", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33859,8 +30162,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "display_name": "Code Llama 13B Python", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33870,8 +30171,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "display_name": "Code Llama 34B", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33881,8 +30180,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "display_name": "Code Llama 34B Instruct", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33892,8 +30189,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "display_name": "Code Llama 34B Python", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33903,8 +30198,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { - "display_name": "Code Llama 70B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33914,8 +30207,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "display_name": "Code Llama 70B Instruct", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33925,8 +30216,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { - "display_name": "Code Llama 70B Python", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -33936,8 +30225,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "display_name": "Code Llama 7B", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33947,8 +30234,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "display_name": "Code Llama 7B Instruct", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33958,8 +30243,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "display_name": "Code Llama 7B Python", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -33969,8 +30252,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "display_name": "Code Qwen 1p5 7B", - "model_vendor": "alibaba", "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, @@ -33980,8 +30261,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "display_name": "Codegemma 2B", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -33991,8 +30270,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "display_name": "Codegemma 7B", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34002,8 +30279,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "display_name": "Cogito 671B V2 P1", - "model_vendor": "cogito", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -34013,8 +30288,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "display_name": "Cogito V1 Preview Llama 3B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34024,8 +30297,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "display_name": "Cogito V1 Preview Llama 70B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34035,8 +30306,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "display_name": "Cogito V1 Preview Llama 8B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34046,8 +30315,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "display_name": "Cogito V1 Preview Qwen 14B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34057,8 +30324,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "display_name": "Cogito V1 Preview Qwen 32B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34068,8 +30333,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { - "display_name": "Flux Kontext Max", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34079,8 +30342,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "display_name": "Dbrx Instruct", - "model_vendor": "databricks", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34090,8 +30351,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "display_name": "Deepseek Coder 1B Base", - "model_vendor": "deepseek", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -34101,8 +30360,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { - "display_name": "Deepseek Coder 33B Instruct", - "model_vendor": "deepseek", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -34112,8 +30369,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "display_name": "Deepseek Coder 7B Base", - "model_vendor": "deepseek", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34123,8 +30378,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "display_name": "Deepseek Coder 7B Base V1p5", - "model_vendor": "deepseek", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34134,8 +30387,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "display_name": "Deepseek Coder 7B Instruct V1p5", - "model_vendor": "deepseek", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34145,8 +30396,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "display_name": "Deepseek Coder V2 Lite Base", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -34156,8 +30405,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "display_name": "Deepseek Coder V2 Lite Instruct", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -34167,8 +30414,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "display_name": "Deepseek Prover V2", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -34178,8 +30423,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "display_name": "Deepseek R1 0528 Distill Qwen3 8B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34189,8 +30432,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "display_name": "Deepseek R1 Distill Llama 70B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34200,8 +30441,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "display_name": "Deepseek R1 Distill Llama 8B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34211,8 +30450,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "display_name": "Deepseek R1 Distill Qwen 14B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34222,8 +30459,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "display_name": "Deepseek R1 Distill Qwen 1p5b", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34233,8 +30468,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "display_name": "Deepseek R1 Distill Qwen 32B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34244,8 +30477,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "display_name": "Deepseek R1 Distill Qwen 7B", - "model_vendor": "deepseek", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34255,8 +30486,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "display_name": "Deepseek V2 Lite Chat", - "model_vendor": "deepseek", "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, @@ -34266,8 +30495,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "display_name": "Deepseek V2p5", - "model_vendor": "deepseek", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34277,8 +30504,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "display_name": "Devstral Small 2505", - "model_vendor": "mistral", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34288,8 +30513,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "display_name": "Dobby Mini Unhinged Plus Llama 3 1 8B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34299,8 +30522,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "display_name": "Dobby Unhinged Llama 3 3 70B New", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34310,8 +30531,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "display_name": "Dolphin 2 9 2 Qwen2 72B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34321,8 +30540,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "display_name": "Dolphin 2p6 Mixtral 8x7b", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34332,8 +30549,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "display_name": "Ernie 4p5 21B A3b Pt", - "model_vendor": "baidu", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34343,8 +30558,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "display_name": "Ernie 4p5 300B A47b Pt", - "model_vendor": "baidu", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34354,8 +30567,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { - "display_name": "Fare 20B", - "model_vendor": "fireworks", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34365,8 +30576,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "display_name": "Firefunction V1", - "model_vendor": "fireworks", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34376,8 +30585,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "display_name": "Firellava 13B", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34387,8 +30594,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "display_name": "Firesearch OCR V6", - "model_vendor": "fireworks", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34398,8 +30603,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { - "display_name": "Fireworks ASR Large", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34409,8 +30612,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { - "display_name": "Fireworks ASR V2", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34420,8 +30621,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "display_name": "Flux 1 Dev", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34431,8 +30630,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { - "display_name": "Flux 1 Dev Controlnet Union", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34442,8 +30639,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { - "display_name": "Flux 1 Dev FP8", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34453,8 +30648,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "display_name": "Flux 1 Schnell", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34464,8 +30657,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { - "display_name": "Flux 1 Schnell FP8", - "model_vendor": "black_forest_labs", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34475,8 +30666,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "display_name": "Gemma 2B It", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34486,8 +30675,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "display_name": "Gemma 3 27B It", - "model_vendor": "google", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34497,8 +30684,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "display_name": "Gemma 7B", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34508,8 +30693,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "display_name": "Gemma 7B It", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34519,8 +30702,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { - "display_name": "Gemma2 9B It", - "model_vendor": "google", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34530,8 +30711,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "display_name": "Glm 4p5v", - "model_vendor": "zhipu", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34542,8 +30721,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "display_name": "GPT Oss Safeguard 120B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34553,8 +30730,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "display_name": "GPT Oss Safeguard 20B", - "model_vendor": "openai", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34564,8 +30739,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "display_name": "Hermes 2 Pro Mistral 7B", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34575,8 +30748,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "display_name": "Internvl3 38B", - "model_vendor": "opengvlab", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -34586,8 +30757,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "display_name": "Internvl3 78B", - "model_vendor": "opengvlab", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -34597,8 +30766,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "display_name": "Internvl3 8B", - "model_vendor": "opengvlab", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -34608,8 +30775,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { - "display_name": "Japanese Stable Diffusion XL", - "model_vendor": "stability", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34619,8 +30784,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { - "display_name": "Kat Coder", - "model_vendor": "fireworks", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -34630,8 +30793,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { - "display_name": "Kat Dev 32B", - "model_vendor": "fireworks", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34641,8 +30802,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "display_name": "Kat Dev 72B Exp", - "model_vendor": "fireworks", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34652,8 +30811,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "display_name": "Llama Guard 2 8B", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34663,8 +30820,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "display_name": "Llama Guard 3 1B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34674,8 +30829,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "display_name": "Llama Guard 3 8B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34685,8 +30838,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "display_name": "Llama V2 13B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34696,8 +30847,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "display_name": "Llama V2 13B Chat", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34707,8 +30856,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "display_name": "Llama V2 70B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34718,8 +30865,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "display_name": "Llama V2 70B Chat", - "model_vendor": "meta", "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, @@ -34729,8 +30874,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "display_name": "Llama V2 7B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34740,8 +30883,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "display_name": "Llama V2 7B Chat", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34751,8 +30892,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "display_name": "Llama V3 70B Instruct", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34762,8 +30901,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { - "display_name": "Llama V3 70B Instruct Hf", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34773,8 +30910,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "display_name": "Llama V3 8B", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34784,8 +30919,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { - "display_name": "Llama V3 8B Instruct Hf", - "model_vendor": "meta", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -34795,8 +30928,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "display_name": "Llama V3p1 405B Instruct Long", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34806,8 +30937,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "display_name": "Llama V3p1 70B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34817,8 +30946,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "display_name": "Llama V3p1 70B Instruct 1B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34828,8 +30955,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "display_name": "Llama V3p1 Nemotron 70B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34839,8 +30964,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "display_name": "Llama V3p2 1B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34850,8 +30973,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "display_name": "Llama V3p2 3B", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34861,8 +30982,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "display_name": "Llama V3p3 70B Instruct", - "model_vendor": "meta", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -34872,8 +30991,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "display_name": "Llamaguard 7B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34883,8 +31000,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "display_name": "Llava Yi 34B", - "model_vendor": "zero_one_ai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34894,8 +31009,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "display_name": "Minimax M1 80K", - "model_vendor": "minimax", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34905,8 +31018,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "display_name": "Minimax M2", - "model_vendor": "minimax", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -34916,8 +31027,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "display_name": "Ministral 3 14B Instruct 2512", - "model_vendor": "mistral", "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, @@ -34927,8 +31036,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "display_name": "Ministral 3 3B Instruct 2512", - "model_vendor": "mistral", "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, @@ -34938,8 +31045,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "display_name": "Ministral 3 8B Instruct 2512", - "model_vendor": "mistral", "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, @@ -34949,8 +31054,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "display_name": "Mistral 7B", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34960,8 +31063,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "display_name": "Mistral 7B Instruct 4K", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34971,8 +31072,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "display_name": "Mistral 7B Instruct V0p2", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34982,8 +31081,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { - "display_name": "Mistral 7B Instruct V3", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -34993,8 +31090,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "display_name": "Mistral 7B V0p2", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35004,8 +31099,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "display_name": "Mistral Large 3 FP8", - "model_vendor": "mistral", "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, @@ -35015,8 +31108,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "display_name": "Mistral Nemo Base 2407", - "model_vendor": "mistral", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35026,8 +31117,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "display_name": "Mistral Nemo Instruct 2407", - "model_vendor": "mistral", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35037,8 +31126,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "display_name": "Mistral Small 24B Instruct 2501", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35048,8 +31135,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "display_name": "Mixtral 8x22b", - "model_vendor": "mistral", "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, @@ -35059,8 +31144,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "display_name": "Mixtral 8x22b Instruct", - "model_vendor": "mistral", "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, @@ -35070,8 +31153,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "display_name": "Mixtral 8x7b", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35081,8 +31162,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "display_name": "Mixtral 8x7b Instruct", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35092,8 +31171,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "display_name": "Mixtral 8x7b Instruct Hf", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35103,8 +31180,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "display_name": "Mythomax L2 13B", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35114,8 +31189,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { - "display_name": "Nemotron Nano V2 12B VL", - "model_vendor": "nvidia", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35125,8 +31198,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "display_name": "Nous Capybara 7B V1p9", - "model_vendor": "nousresearch", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35136,8 +31207,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { - "display_name": "Nous Hermes 2 Mixtral 8x7b DPO", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35147,8 +31216,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "display_name": "Nous Hermes 2 Yi 34B", - "model_vendor": "zero_one_ai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35158,8 +31225,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "display_name": "Nous Hermes Llama2 13B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35169,8 +31234,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "display_name": "Nous Hermes Llama2 70B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35180,8 +31243,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "display_name": "Nous Hermes Llama2 7B", - "model_vendor": "meta", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35191,8 +31252,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "display_name": "Nvidia Nemotron Nano 12B V2", - "model_vendor": "nvidia", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35202,8 +31261,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "display_name": "Nvidia Nemotron Nano 9B V2", - "model_vendor": "nvidia", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35213,8 +31270,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "display_name": "Openchat 3p5 0106 7B", - "model_vendor": "fireworks", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -35224,8 +31279,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "display_name": "Openhermes 2 Mistral 7B", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35235,8 +31288,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { - "display_name": "Openhermes 2p5 Mistral 7B", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35246,8 +31297,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "display_name": "Openorca 7B", - "model_vendor": "fireworks", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35257,8 +31306,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "display_name": "Phi 2 3B", - "model_vendor": "microsoft", "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, @@ -35268,8 +31315,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "display_name": "Phi 3 Mini 128K Instruct", - "model_vendor": "microsoft", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35279,8 +31324,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "display_name": "Phi 3 Vision 128K Instruct", - "model_vendor": "microsoft", "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, @@ -35290,8 +31333,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "display_name": "Phind Code Llama 34B Python V1", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -35301,8 +31342,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "display_name": "Phind Code Llama 34B V1", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -35312,8 +31351,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "display_name": "Phind Code Llama 34B V2", - "model_vendor": "meta", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -35323,8 +31360,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { - "display_name": "Playground V2 1024px Aesthetic", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35334,8 +31369,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { - "display_name": "Playground V2 5 1024px Aesthetic", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35345,8 +31378,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "display_name": "Pythia 12B", - "model_vendor": "fireworks", "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, @@ -35356,8 +31387,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "display_name": "Qwen Qwq 32B Preview", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35367,8 +31396,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "display_name": "Qwen V2p5 14B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35378,8 +31405,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "display_name": "Qwen V2p5 7B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35389,8 +31414,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "display_name": "Qwen1p5 72B Chat", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35400,8 +31423,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "display_name": "Qwen2 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35411,8 +31432,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "display_name": "Qwen2 VL 2B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35422,8 +31441,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "display_name": "Qwen2 VL 72B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35433,8 +31450,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "display_name": "Qwen2 VL 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35444,8 +31459,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "display_name": "Qwen2p5 0p5b Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35455,8 +31468,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "display_name": "Qwen2p5 14B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35466,8 +31477,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "display_name": "Qwen2p5 1p5b Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35477,8 +31486,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "display_name": "Qwen2p5 32B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35488,8 +31495,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "display_name": "Qwen2p5 32B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35499,8 +31504,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "display_name": "Qwen2p5 72B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35510,8 +31513,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "display_name": "Qwen2p5 72B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35521,8 +31522,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "display_name": "Qwen2p5 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35532,8 +31531,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "display_name": "Qwen2p5 Coder 0p5b", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35543,8 +31540,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "display_name": "Qwen2p5 Coder 0p5b Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35554,8 +31549,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "display_name": "Qwen2p5 Coder 14B", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35565,8 +31558,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "display_name": "Qwen2p5 Coder 14B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35576,8 +31567,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "display_name": "Qwen2p5 Coder 1p5b", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35587,8 +31576,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "display_name": "Qwen2p5 Coder 1p5b Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35598,8 +31585,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "display_name": "Qwen2p5 Coder 32B", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35609,8 +31594,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "display_name": "Qwen2p5 Coder 32B Instruct 128K", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35620,8 +31603,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "display_name": "Qwen2p5 Coder 32B Instruct 32K Rope", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35631,8 +31612,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "display_name": "Qwen2p5 Coder 32B Instruct 64K", - "model_vendor": "alibaba", "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, @@ -35642,8 +31621,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "display_name": "Qwen2p5 Coder 3B", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35653,8 +31630,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "display_name": "Qwen2p5 Coder 3B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35664,8 +31639,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "display_name": "Qwen2p5 Coder 7B", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35675,8 +31648,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "display_name": "Qwen2p5 Coder 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35686,8 +31657,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "display_name": "Qwen2p5 Math 72B Instruct", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35697,8 +31666,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "display_name": "Qwen2p5 VL 32B Instruct", - "model_vendor": "alibaba", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35708,8 +31675,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "display_name": "Qwen2p5 VL 3B Instruct", - "model_vendor": "alibaba", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35719,8 +31684,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "display_name": "Qwen2p5 VL 72B Instruct", - "model_vendor": "alibaba", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35730,8 +31693,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { - "display_name": "Qwen2p5 VL 7B Instruct", - "model_vendor": "alibaba", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -35741,8 +31702,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "display_name": "Qwen3 0p6b", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35752,8 +31711,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "display_name": "Qwen3 14B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35763,8 +31720,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "display_name": "Qwen3 1p7b", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35774,8 +31729,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "display_name": "Qwen3 1p7b FP8 Draft", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35785,8 +31738,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "display_name": "Qwen3 1p7b FP8 Draft 131072", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35796,8 +31747,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "display_name": "Qwen3 1p7b FP8 Draft 40960", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35807,8 +31756,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "display_name": "Qwen3 235B A22b", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35818,8 +31765,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "display_name": "Qwen3 235B A22b Instruct 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35829,8 +31774,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "display_name": "Qwen3 235B A22b Thinking 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35840,8 +31783,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "display_name": "Qwen3 30B A3b", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -35851,8 +31792,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "display_name": "Qwen3 30B A3b Instruct 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35862,8 +31801,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "display_name": "Qwen3 30B A3b Thinking 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35873,19 +31810,16 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "display_name": "Qwen3 32B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "display_name": "Qwen3 4B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35895,8 +31829,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "display_name": "Qwen3 4B Instruct 2507", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35906,19 +31838,16 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "display_name": "Qwen3 8B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "display_name": "Qwen3 Coder 30B A3b Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -35928,8 +31857,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "display_name": "Qwen3 Coder 480B Instruct BF16", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35939,8 +31866,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { - "display_name": "Qwen3 Embedding 0p6b", - "model_vendor": "alibaba", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -35950,8 +31875,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { - "display_name": "Qwen3 Embedding 4B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35961,8 +31884,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/": { - "display_name": "", - "model_vendor": "fireworks", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -35972,8 +31893,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "display_name": "Qwen3 Next 80B A3b Instruct", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35983,8 +31902,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "display_name": "Qwen3 Next 80B A3b Thinking", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -35994,8 +31911,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { - "display_name": "Qwen3 Reranker 0p6b", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -36005,8 +31920,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { - "display_name": "Qwen3 Reranker 4B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -36016,8 +31929,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { - "display_name": "Qwen3 Reranker 8B", - "model_vendor": "alibaba", "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, @@ -36027,8 +31938,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "display_name": "Qwen3 VL 235B A22b Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -36038,8 +31947,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "display_name": "Qwen3 VL 235B A22b Thinking", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -36049,8 +31956,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "display_name": "Qwen3 VL 30B A3b Instruct", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -36060,8 +31965,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "display_name": "Qwen3 VL 30B A3b Thinking", - "model_vendor": "alibaba", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -36071,8 +31974,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "display_name": "Qwen3 VL 32B Instruct", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36082,8 +31983,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "display_name": "Qwen3 VL 8B Instruct", - "model_vendor": "alibaba", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36093,8 +31992,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "display_name": "Qwq 32B", - "model_vendor": "alibaba", "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -36104,8 +32001,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "display_name": "Rolm OCR", - "model_vendor": "fireworks", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -36115,8 +32010,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "display_name": "Snorkel Mistral 7B Pairrm DPO", - "model_vendor": "mistral", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -36126,8 +32019,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { - "display_name": "Stable Diffusion XL 1024 V1 0", - "model_vendor": "stability", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36137,8 +32028,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "display_name": "Stablecode 3B", - "model_vendor": "fireworks", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36148,8 +32037,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "display_name": "Starcoder 16B", - "model_vendor": "bigcode", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -36159,8 +32046,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "display_name": "Starcoder 7B", - "model_vendor": "bigcode", "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, @@ -36170,8 +32055,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "display_name": "Starcoder2 15B", - "model_vendor": "bigcode", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -36181,8 +32064,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "display_name": "Starcoder2 3B", - "model_vendor": "bigcode", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -36192,8 +32073,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "display_name": "Starcoder2 7B", - "model_vendor": "bigcode", "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -36203,8 +32082,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "display_name": "Toppy M 7B", - "model_vendor": "fireworks", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -36214,8 +32091,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/whisper-v3": { - "display_name": "Whisper V3", - "model_vendor": "openai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36225,8 +32100,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/whisper-v3-turbo": { - "display_name": "Whisper V3 Turbo", - "model_vendor": "openai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36236,8 +32109,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { - "display_name": "Yi 34B", - "model_vendor": "zero_one_ai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36247,8 +32118,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "display_name": "Yi 34B 200K Capybara", - "model_vendor": "zero_one_ai", "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, @@ -36258,8 +32127,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "display_name": "Yi 34B Chat", - "model_vendor": "zero_one_ai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36269,8 +32136,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { - "display_name": "Yi 6B", - "model_vendor": "zero_one_ai", "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, @@ -36280,8 +32145,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "display_name": "Zephyr 7B Beta", - "model_vendor": "fireworks", "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f45c76f145..5baa9e1aa3 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -15832,8 +15832,6 @@ "mode": "embedding" }, "gigachat/GigaChat-2-Lite": { - "display_name": "GigaChat 2 Lite", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, @@ -15845,8 +15843,6 @@ "supports_system_messages": true }, "gigachat/GigaChat-2-Max": { - "display_name": "GigaChat 2 Max", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, @@ -15859,8 +15855,6 @@ "supports_vision": true }, "gigachat/GigaChat-2-Pro": { - "display_name": "GigaChat 2 Pro", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, @@ -15873,8 +15867,6 @@ "supports_vision": true }, "gigachat/Embeddings": { - "display_name": "GigaChat Embeddings", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, @@ -15884,8 +15876,6 @@ "output_vector_size": 1024 }, "gigachat/Embeddings-2": { - "display_name": "GigaChat Embeddings 2", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, @@ -15895,8 +15885,6 @@ "output_vector_size": 1024 }, "gigachat/EmbeddingsGigaR": { - "display_name": "GigaChat Embeddings GigaR", - "model_vendor": "sberbank", "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096,