# MiniMax M3

> Open-weight frontier model: frontier coding, 1M context, and native multimodality in one.

- Maker: MiniMax
- Line: MiniMax M-Series
- Canonical page: https://ai-tldr.dev/models/minimax-m3/
- Updated: 2026-06-18

## In short

MiniMax M3 is an open-weight model from MiniMax. MiniMax released it on 1 June 2026. It has a 1M-token context window and costs $0.60 per million input tokens and $2.40 per million output tokens. You can use it through MiniMax and OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 1M | [1] |
| Input price | $0.60 / 1M tokens | [2] |
| Output price | $2.40 / 1M tokens | [2] |
| Licence | MiniMax Community License · open weights | [1] |
| Released | 1 June 2026 | [3] |
| Parameters | ~428B total / ~23B active | [1] |

## Sources

1. [Model card (Hugging Face)](https://huggingface.co/MiniMaxAI/MiniMax-M3)
2. [MiniMax blog — MiniMax M3](https://www.minimax.io/blog/minimax-m3)
3. [MiniMax (official site)](https://www.minimax.io)

## Overview

MiniMax-M3 is an open-weight frontier model released June 1, 2026, billed by MiniMax as the first open-weight model to combine top-tier coding and agentic performance, a 1M-token context window, and native multimodality in a single architecture.

It is a sparse Mixture-of-Experts model with roughly 428B total parameters and about 23B activated per token, powered by MiniMax Sparse Attention (MSA). MSA cuts per-token compute at full context length and delivers large prefill and decode speedups versus M2 at 1M context. The model supports text, image, and video input and offers toggleable reasoning (thinking on/off) at identical pricing.

Weights are openly downloadable on Hugging Face under the MiniMax Community License. MiniMax reports strong agentic and coding results and aggressive pricing through its platform.

## Benchmarks

- SWE-Bench Pro: 59% ([source](https://www.minimax.io/blog/minimax-m3))
- Terminal-Bench 2.1: 66% ([source](https://www.minimax.io/blog/minimax-m3))
- MCP Atlas: 74.2% ([source](https://www.minimax.io/blog/minimax-m3))
- KernelBench Hard: 28.8% ([source](https://www.minimax.io/blog/minimax-m3))
- SWE-fficiency: 34.8% ([source](https://www.minimax.io/blog/minimax-m3))

## Pricing

- Input: $0.60 / 1M tokens
- Output: $2.40 / 1M tokens

Source: https://www.minimax.io/blog/minimax-m3

## Strengths

- 1 million token context window with efficient MiniMax Sparse Attention
- Open weights for self-hosting and customization
- Native multimodal input (text, image, video)
- Frontier-level coding and agentic benchmark scores
- Toggleable reasoning modes at the same price

## Best for

- Long-horizon agentic coding and software engineering
- Ultra-long-document and full-repository understanding
- Multimodal applications across text, image, and video
- Self-hosted frontier-class deployments

## How to access

- [MiniMax](https://platform.minimax.io) — model id `MiniMax-M3`
- [OpenRouter](https://openrouter.ai/minimax/minimax-m3) — model id `minimax/minimax-m3`

## MiniMax M-Series versions

- MiniMax M3 (1 June 2026) — this page
- [MiniMax M2.7 / M2.7-highspeed](https://ai-tldr.dev/models/minimax-m2-7/) (18 March 2026)
- [MiniMax M2.5 / M2.5-Lightning](https://ai-tldr.dev/models/minimax-m2-5/) (12 February 2026)
- [MiniMax M2.1](https://ai-tldr.dev/models/minimax-m2-1/) (23 December 2025)
- [MiniMax M2](https://ai-tldr.dev/models/minimax-m2/) (27 October 2025)

## FAQ

### Is MiniMax-M3 open weights?

Yes. MiniMax released M3's weights openly on Hugging Face (MiniMaxAI/MiniMax-M3) under the MiniMax Community License, in Safetensors format. MiniMax describes it as the first open-weight model to combine frontier coding, a 1M-token context window, and native multimodality, enabling self-hosting and enterprise customization.

### What is MiniMax Sparse Attention (MSA)?

MSA is the sparse attention operator behind MiniMax-M3, designed for million-token contexts. It reduces per-token compute at full context length to a fraction of the previous generation while preserving quality, yielding large prefill and decode speedups over M2 at 1M context and making long-context inference far cheaper.

### How much does MiniMax-M3 cost?

Through MiniMax's platform, M3 is priced at $0.60 per 1M input tokens and $2.40 per 1M output tokens for prompts at or below 512K tokens, with a higher long-context rate above 512K. A launch promotion temporarily halved these to $0.30 input and $1.20 output.

### What benchmarks does MiniMax-M3 report?

Per MiniMax's official blog, M3 scores 59.0% on SWE-Bench Pro, 66.0% on Terminal-Bench 2.1, 74.2% on MCP Atlas, 28.8% on KernelBench Hard, and 34.8% on SWE-fficiency. MiniMax positions these as frontier-level agentic and coding results at a fraction of comparable proprietary model costs.

## Links

- [MiniMax blog — MiniMax M3](https://www.minimax.io/blog/minimax-m3)
- [Model card (Hugging Face)](https://huggingface.co/MiniMaxAI/MiniMax-M3)
- [MiniMax (official site)](https://www.minimax.io)
- [GitHub — MiniMax-M3](https://github.com/MiniMax-AI/MiniMax-M3)
- [MiniMax Sparse Attention (paper)](https://arxiv.org/abs/2606.13392)
- [MiniMax M3 on OpenRouter](https://openrouter.ai/minimax/minimax-m3)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/minimax-m3/