From 8afbbe44a5701a2273e041060cee76bed296d272 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Sat, 3 May 2025 15:47:43 +0100 Subject: [PATCH 1/3] Update OpenAPI to version generated from ref 7e3279dcb9e884e7c31f1b1218c59892f5ccc4b5 (#1398) Co-authored-by: github-actions[bot] --- api/openapi.json | 2 ++ 1 file changed, 2 insertions(+) diff --git a/api/openapi.json b/api/openapi.json index 759231de..e92cbdb5 100644 --- a/api/openapi.json +++ b/api/openapi.json @@ -1599,6 +1599,7 @@ }, "name": { "type": "string", + "minLength": 3, "title": "Name" }, "description": { @@ -2337,6 +2338,7 @@ }, "name": { "type": "string", + "minLength": 3, "title": "Name" }, "description": { From 24e08e556ac1a725bfff7064a84964cb7e217646 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Sun, 4 May 2025 08:29:24 +0300 Subject: [PATCH 2/3] Update model_prices_and_context_window.json to version generated on 2025-05-04 (#1399) Co-authored-by: github-actions[bot] --- .../model_prices_and_context_window.json | 331 +++++++++++++++--- 1 file changed, 289 insertions(+), 42 deletions(-) diff --git a/model_cost_data/model_prices_and_context_window.json b/model_cost_data/model_prices_and_context_window.json index fdca26b0..e81ff3c5 100644 --- a/model_cost_data/model_prices_and_context_window.json +++ b/model_cost_data/model_prices_and_context_window.json @@ -602,6 +602,26 @@ "supports_vision": true, "supports_prompt_caching": true }, + "computer-use-preview": { + "max_tokens": 1024, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "input_cost_per_token": 3e-6, + "output_cost_per_token": 12e-6, + "litellm_provider": "azure", + "mode": "chat", + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true + }, "o3": { "max_tokens": 100000, "max_input_tokens": 200000, @@ -1547,12 +1567,23 @@ "litellm_provider": "openai", "supported_endpoints": ["/v1/audio/speech"] }, + "gpt-4o-mini-tts": { + "mode": "audio_speech", + "input_cost_per_token": 2.5e-6, + "output_cost_per_token": 10e-6, + "output_cost_per_audio_token": 12e-6, + "output_cost_per_second": 0.00025, + "litellm_provider": "openai", + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["audio"], + "supported_endpoints": ["/v1/audio/speech"] + }, "azure/computer-use-preview": { "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000012, + "input_cost_per_token": 3e-6, + "output_cost_per_token": 12e-6, "litellm_provider": "azure", "mode": "chat", "supported_endpoints": ["/v1/responses"], @@ -4829,6 +4860,54 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "max_tokens": 128000, + "max_input_tokens": 10000000, + "max_output_tokens": 4028, + "litellm_provider": "meta_llama", + "mode": "chat", + "supports_function_calling": false, + "source": "https://llama.developer.meta.com/docs/models", + "supports_tool_choice": false, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"] + }, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "max_tokens": 128000, + "max_input_tokens": 1000000, + "max_output_tokens": 4028, + "litellm_provider": "meta_llama", + "mode": "chat", + "supports_function_calling": false, + "source": "https://llama.developer.meta.com/docs/models", + "supports_tool_choice": false, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"] + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "litellm_provider": "meta_llama", + "mode": "chat", + "supports_function_calling": false, + "source": "https://llama.developer.meta.com/docs/models", + "supports_tool_choice": false, + "supported_modalities": ["text"], + "supported_output_modalities": ["text"] + }, + "meta_llama/Llama-3.3-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "litellm_provider": "meta_llama", + "mode": "chat", + "supports_function_calling": false, + "source": "https://llama.developer.meta.com/docs/models", + "supports_tool_choice": false, + "supported_modalities": ["text"], + "supported_output_modalities": ["text"] + }, "gemini-pro": { "max_tokens": 8192, "max_input_tokens": 32760, @@ -5564,6 +5643,8 @@ "output_cost_per_token_above_200k_tokens": 0.0, "litellm_provider": "gemini", "mode": "chat", + "rpm": 5, + "tpm": 250000, "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, @@ -6276,6 +6357,62 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true }, + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "max_tokens": 10e6, + "max_input_tokens": 10e6, + "max_output_tokens": 10e6, + "input_cost_per_token": 0.25e-6, + "output_cost_per_token": 0.70e-6, + "litellm_provider": "vertex_ai-llama_models", + "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "supports_function_calling": true, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"] + }, + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "max_tokens": 10e6, + "max_input_tokens": 10e6, + "max_output_tokens": 10e6, + "input_cost_per_token": 0.25e-6, + "output_cost_per_token": 0.70e-6, + "litellm_provider": "vertex_ai-llama_models", + "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "supports_function_calling": true, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"] + }, + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "max_tokens": 1e6, + "max_input_tokens": 1e6, + "max_output_tokens": 1e6, + "input_cost_per_token": 0.35e-6, + "output_cost_per_token": 1.15e-6, + "litellm_provider": "vertex_ai-llama_models", + "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "supports_function_calling": true, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"] + }, + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "max_tokens": 1e6, + "max_input_tokens": 1e6, + "max_output_tokens": 1e6, + "input_cost_per_token": 0.35e-6, + "output_cost_per_token": 1.15e-6, + "litellm_provider": "vertex_ai-llama_models", + "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "supports_function_calling": true, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"] + }, "vertex_ai/meta/llama3-70b-instruct-maas": { "max_tokens": 32000, "max_input_tokens": 32000, @@ -8648,6 +8785,20 @@ "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "us.amazon.nova-premier-v1:0": { + "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.0000125, + "litellm_provider": "bedrock_converse", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true + }, "anthropic.claude-3-sonnet-20240229-v1:0": { "max_tokens": 4096, "max_input_tokens": 200000, @@ -8705,6 +8856,7 @@ "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_response_schema": true, + "supports_pdf_input": true, "supports_reasoning": true, "supports_tool_choice": true }, @@ -8823,6 +8975,7 @@ "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_response_schema": true, + "supports_pdf_input": true, "supports_tool_choice": true, "supports_reasoning": true }, @@ -10213,6 +10366,55 @@ "mode": "chat", "supports_tool_choice": true }, + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "litellm_provider": "together_ai", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "mode": "chat", + "supports_tool_choice": true + }, "ollama/codegemma": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -10740,42 +10942,6 @@ "mode": "chat" , "deprecation_date": "2025-02-22" }, - "perplexity/sonar": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000001, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-pro": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 8096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000001, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-pro": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 8096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "perplexity", - "mode": "chat" - }, "perplexity/pplx-7b-chat": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -10879,6 +11045,23 @@ "litellm_provider": "perplexity", "mode": "chat" }, + "perplexity/sonar-deep-research": { + "max_tokens": 12000, + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "output_cost_per_reasoning_token": 3e-5, + "litellm_provider": "perplexity", + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_low": 5e-3, + "search_context_size_medium": 5e-3, + "search_context_size_high": 5e-3 + }, + "supports_reasoning": true, + "supports_web_search": true + }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "max_tokens": 16384, "max_input_tokens": 16384, @@ -11013,7 +11196,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { "max_tokens": 65536, "max_input_tokens": 65536, - "max_output_tokens": 8192, + "max_output_tokens": 65536, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", @@ -11035,7 +11218,66 @@ "source": "https://fireworks.ai/pricing", "supports_tool_choice": true }, - + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "max_tokens": 20480, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "input_cost_per_token": 3e-6, + "output_cost_per_token": 8e-6, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_response_schema": true, + "source": "https://fireworks.ai/pricing", + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "max_tokens": 20480, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "input_cost_per_token": 0.55e-6, + "output_cost_per_token": 2.19e-6, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_response_schema": true, + "source": "https://fireworks.ai/pricing", + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-6, + "output_cost_per_token": 3e-6, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_response_schema": true, + "source": "https://fireworks.ai/pricing", + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.22e-6, + "output_cost_per_token": 0.88e-6, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_response_schema": true, + "source": "https://fireworks.ai/pricing", + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.15e-6, + "output_cost_per_token": 0.60e-6, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_response_schema": true, + "source": "https://fireworks.ai/pricing", + "supports_tool_choice": true + }, "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -11081,12 +11323,17 @@ "mode": "embedding", "source": "https://fireworks.ai/pricing" }, - "fireworks-ai-up-to-16b": { + "fireworks-ai-up-to-4b": { + "input_cost_per_token": 0.0000002, + "output_cost_per_token": 0.0000002, + "litellm_provider": "fireworks_ai" + }, + "fireworks-ai-4.1b-to-16b": { "input_cost_per_token": 0.0000002, "output_cost_per_token": 0.0000002, "litellm_provider": "fireworks_ai" }, - "fireworks-ai-16.1b-to-80b": { + "fireworks-ai-above-16b": { "input_cost_per_token": 0.0000009, "output_cost_per_token": 0.0000009, "litellm_provider": "fireworks_ai" From 6bd3c4c88717389d0d617b3992d5b23f38d5618e Mon Sep 17 00:00:00 2001 From: Brian Dussault Date: Thu, 5 Jun 2025 00:41:24 -0400 Subject: [PATCH 3/3] Update README.md (#1419) Add deprecation notice. --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 3a0717de..93bb9cec 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ +# ⚠️ DEPRECATED ⚠️ + +CodeGate was an experimental project and is no longer maintained. + CodeGate logo