From 35cd56f99053999aec6c76683fcba78b5a1ec342 Mon Sep 17 00:00:00 2001 From: Ethan Clarke Date: Thu, 12 Mar 2026 20:41:46 +0800 Subject: [PATCH] feat: add MiniMax-M2.5 and M2.5-highspeed models (#13557) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## Summary Add MiniMax's latest M2.5 model family to the model registry and update the default API base URL to the international endpoint for broader accessibility. ## Changes - **Add MiniMax-M2.5 models** to `conf/llm_factories.json`: - `MiniMax-M2.5` — Peak Performance. Ultimate Value. Master the Complex. - `MiniMax-M2.5-highspeed` — Same performance, faster and more agile. - Both support 204,800 token context window and tool calling (`is_tools: true`). - **Update default MiniMax API base URL** in `rag/llm/__init__.py`: - From `https://api.minimaxi.com/v1` (domestic) to `https://api.minimax.io/v1` (international). - Chinese users can still override via the Base URL field in the UI settings (as documented in existing i18n strings). ## Supported Models | Model | Context Window | Tool Calling | Description | |-------|---------------|-------------|-------------| | `MiniMax-M2.5` | 204,800 tokens | Yes | Peak Performance. Ultimate Value. | | `MiniMax-M2.5-highspeed` | 204,800 tokens | Yes | Same performance, faster and more agile. | ## API Documentation - OpenAI Compatible API: https://platform.minimax.io/docs/api-reference/text-openai-api ## Testing - [x] JSON validation passes - [x] Python syntax validation passes - [x] Ruff lint passes - [x] MiniMax-M2.5 API call verified (returns valid response) - [x] MiniMax-M2.5-highspeed API call verified (returns valid response) Co-authored-by: PR Bot Co-authored-by: Jin Hai Co-authored-by: Yingfeng --- conf/llm_factories.json | 14 ++++++++++++++ rag/llm/__init__.py | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/conf/llm_factories.json b/conf/llm_factories.json index 20ef720f1a..170e22340c 100644 --- a/conf/llm_factories.json +++ b/conf/llm_factories.json @@ -1300,6 +1300,20 @@ "rank": "810", "url": "https://api.minimaxi.com/v1", "llm": [ + { + "llm_name": "MiniMax-M2.5", + "tags": "LLM,CHAT,200k", + "max_tokens": 204800, + "model_type": "chat", + "is_tools": true + }, + { + "llm_name": "MiniMax-M2.5-highspeed", + "tags": "LLM,CHAT,200k", + "max_tokens": 204800, + "model_type": "chat", + "is_tools": true + }, { "llm_name": "MiniMax-M2.1", "tags": "LLM,CHAT,200k", diff --git a/rag/llm/__init__.py b/rag/llm/__init__.py index 77b1ff2b0e..9cbce5acd9 100644 --- a/rag/llm/__init__.py +++ b/rag/llm/__init__.py @@ -81,7 +81,7 @@ FACTORY_DEFAULT_BASE_URL = { SupportedLiteLLMProvider.Anthropic: "https://api.anthropic.com/", SupportedLiteLLMProvider.JiekouAI: "https://api.jiekou.ai/openai", SupportedLiteLLMProvider.ZHIPU_AI: "https://open.bigmodel.cn/api/paas/v4", - SupportedLiteLLMProvider.MiniMax: "https://api.minimaxi.com/v1", + SupportedLiteLLMProvider.MiniMax: "https://api.minimax.io/v1", SupportedLiteLLMProvider.DeerAPI: "https://api.deerapi.com/v1", SupportedLiteLLMProvider.OpenAI: "https://api.openai.com/v1", SupportedLiteLLMProvider.n1n: "https://api.n1n.ai/v1",