# MiniMax M3.1 Flash: Redefining Agent Performance and Cost - MiniMax Research

Flat pricing is set at $0.15 per 1M input tokens, $0.60 per 1M output tokens, and $0.015 per 1M cached input tokens.

- Output speeds reach over 200 tokens per second with a median P50 speed of 170+ TPS.
- Available immediately through the MiniMax API, M Plan, and MiniMax Code, with model weights scheduled for a later release.
- Scores 73.7% on DeepSWE v1.1, 61.7 points on OSWorld V2, and 82% on CyberGym.
- Reduces overall usage costs for agentic tasks by 70% compared to its predecessor.

## Why it matters

Developers building coding and agentic computer-use tools can access frontier-level benchmark capabilities at higher inference speeds and lower token costs.

## Sources

- [MiniMax: MiniMax M3.1 Flash: Redefining Agent Performance and Cost - MiniMax Research](https://www.minimax.io/blog/minimax-m31f)

---

Summarized by dstilled on 2026-10-19. https://dstilled.ai/story/a9d028d7-6344-4edd-8b1d-2bff83fbc0ef