Favicon für 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.

Modalitäten
Kontext
1,0M
Veröffentlicht
17. Juni 2025
Wissensstand
Juni 2024

Aktivität

Token-Volumen und Anfrageaufkommen für dieses Modell im Zeitverlauf.

Derzeit nicht über EU-regionales Routing verfügbar. Dokumentation zum regionsinternen Routing

Häufig gestellte Fragen

Weitere Modelle entdecken