MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors. Benchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency. 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 |
|---|---|---|---|
| Benchmarksjust now | 60 | 30% | +17.9 |
| Recencyjust now | 100 | 15% | +15.0 |
| Capabilitiesjust now | 67 | 20% | +13.3 |
| Output Capacityjust now | 88 | 10% | +8.8 |
| Context Windowjust now | 84 | 10% | +8.4 |
| Pricingjust now | 1 | 15% | +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 and help the community make better decisions.
成本估算器
每月比类别平均节省$37.76
来自已验证的来源。