MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency. Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).
| 信号 | 强度 | 权重 | 影响 |
|---|---|---|---|
| Capabilitiesjust now | 67 | 30% | +20.0 |
| Recencyjust now | 100 | 15% | +15.0 |
| Context Windowjust now | 84 | 15% | +12.6 |
| Output Capacityjust now | 20 | 15% | +3.0 |
| Pricingjust now | 1 | 25% | +0.2 |
社区和从业者反馈在基准测试和价格之上增加了真实世界的信号。
Share your experience with MiniMax M2.1 and help the community make better decisions.
成本估算器
每月比类别平均节省$37.80