# MiniMax M3: AI model fact sheet

- **Provider:** minimax
- **Released:** 2026-06-01
- **Context window:** 1,048,576 tokens
- **API pricing:** $0.30 / 1M input, $1.20 / 1M output
- **OpenRouter ID:** minimax/minimax-m3
- **Capabilities:** conversation, reasoning, code-generation, analysis, agentic-tool-use, tool-use, planning

MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video inputs and produces text output, with a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context, roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, it is oriented toward sustained, multi-step tasks rather than single-turn execution.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| SWE-Bench Pro | 59.0% |
| Terminal-Bench 2.1 | 66.0% |
| SWE-fficiency | 34.8% |
| KernelBench Hard | 28.8% |
| MCP Atlas | 74.2% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/minimax-m3