← Back to models

MiniMax-M1

MiniMax AI (China) June 16 2025

Parameters

456B / 45.9B (MoE)

License

Open (permissive)

Key Features

Hybrid-attention reasoning model; Lightning attention for efficient scaling; 1M token context; RL with CISPO; outperforms DeepSeek-R1 on SWE-bench/GPQA; function calling/agentic tools.