# MiniMax M2: AI model fact sheet

- **Provider:** minimax
- **Released:** 2025-10-23
- **Context window:** 204,800 tokens
- **API pricing:** $0.000 / 1M input, $0.000 / 1M output
- **OpenRouter ID:** minimax/minimax-m2:free
- **Capabilities:** conversation, reasoning, code-generation, analysis, planning, agentic-tool-use, tool-use

MiniMax M2 is a high-efficiency 10B activated parameter model optimized for coding agents, compile-run-fix loops, and long-horizon reasoning. It balances responsiveness with strong SWE-Bench and Terminal-Bench results, excels at code generation, planning, and tool use, and preserves reasoning continuity across multi-step tasks.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| SWE-bench Verified | 69.4% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/minimax-m2-free