Favicon de minimax

MiniMax: MiniMax M1

minimax/minimax-m1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks.

Trained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.

Modalités
Contexte
1,0M
Publié
17 juin 2025
Date limite des connaissances
juin 2024

Activité

Volume de jetons et trafic des requêtes vers ce modèle au fil du temps.

Actuellement indisponible via le routage dans la région UE. Documentation sur le routage intrarégional

Questions fréquentes

Explorer d’autres modèles