From e2ac3fbc83e32d4bb9e0b71f93c6513ab795aa9b Mon Sep 17 00:00:00 2001 From: isaken Date: Sat, 5 Jul 2025 18:01:46 +0200 Subject: [PATCH] Patch 1 (#12338) * add watsonx/mistralai/mistral-large to model prices and context window json - Set max_tokens and max_input_tokens to 131072 and max_output_tokens to 16384 to match IBM's official context window limit for Mistral Large models hosted on watsonx. - Correct input_cost_per_token and output_cost_per_token to reflect IBM's pricing of $0.003 and $0.01 per 1000 tokens, respectively, converted to per-token rates (0.000003 and 0.00001). - Confirmed function-calling support based on IBM documentation and Mistral's own API schema. - Aligns with Mistral's own model entries that specify token windows of ~128K and matches LiteLLM's expected cost format. **Sources:** - IBM watsonx Foundation Models docs: https://www.ibm.com/docs/en/watsonx/w-and-w/2.1.x?topic=models-foundation-model-details#mistral-large - IBM Pricing information for watsonx.ai models: https://www.ibm.com/products/watsonx-ai/pricing - LiteLLM repo docs on token cost formatting and limits https://docs.litellm.ai/docs/proxy/custom_pricing. - Imitating entries from litellm/model_prices_and_context_window.json for watsonx/ibm/granite-3-8b-instruct as well as Mistral's own mistral/mistral-large-latest and similar. * Update model_prices_and_context_window.json typo * Update model_prices_and_context_window.json * Update model_prices_and_context_window.json --- model_prices_and_context_window.json | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 05f1371673..7d21ec9a96 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -314,6 +314,24 @@ "supports_response_schema": true, "supports_system_messages": true }, + "watsonx/mistralai/mistral-large": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.00001, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_parallel_function_calling": false, + "supports_vision": false, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true + }, "gpt-4o-search-preview-2025-03-11": { "max_tokens": 16384, "max_input_tokens": 128000,