From b1ba305dbf2f1cc4fb5c1b04bf945fce64399f00 Mon Sep 17 00:00:00 2001 From: octo-patch Date: Mon, 1 Jun 2026 23:39:38 +0800 Subject: [PATCH] feat: upgrade MiniMax default model to M3 - Set MiniMax-M3 as the new default in the API config - Update example to use MiniMax-M3 and refresh the available models list - Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed; drop the deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed entries from the example MiniMax-M3 is the new flagship model with 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. Co-Authored-By: Octopus --- examples/basic_modules/llm.py | 6 +++--- src/memos/api/config.py | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/examples/basic_modules/llm.py b/examples/basic_modules/llm.py index 3fd7352c7..fa82a45dc 100644 --- a/examples/basic_modules/llm.py +++ b/examples/basic_modules/llm.py @@ -167,14 +167,14 @@ # Scenario 7: Using LLMFactory with MiniMax (OpenAI-compatible API) # Prerequisites: # 1. Get your API key from the MiniMax platform. -# 2. Available models: MiniMax-M2.7 (flagship), MiniMax-M2.7-highspeed (low-latency), -# MiniMax-M2.5, MiniMax-M2.5-highspeed. +# 2. Available models: MiniMax-M3 (flagship, default), MiniMax-M2.7, +# MiniMax-M2.7-highspeed (low-latency). cfg_mm = LLMConfigFactory.model_validate( { "backend": "minimax", "config": { - "model_name_or_path": "MiniMax-M2.7", + "model_name_or_path": "MiniMax-M3", "api_key": "your-minimax-api-key", "api_base": "https://api.minimax.io/v1", "temperature": 0.7, diff --git a/src/memos/api/config.py b/src/memos/api/config.py index 69efedeb3..3de2947d9 100644 --- a/src/memos/api/config.py +++ b/src/memos/api/config.py @@ -288,7 +288,7 @@ def qwen_config() -> dict[str, Any]: def minimax_config() -> dict[str, Any]: """Get MiniMax configuration.""" return { - "model_name_or_path": os.getenv("MOS_CHAT_MODEL", "MiniMax-M2.7"), + "model_name_or_path": os.getenv("MOS_CHAT_MODEL", "MiniMax-M3"), "temperature": float(os.getenv("MOS_CHAT_TEMPERATURE", "0.8")), "max_tokens": int(os.getenv("MOS_MAX_TOKENS", "8000")), "top_p": float(os.getenv("MOS_TOP_P", "0.9")),