# MiniMax M2.5

SOTA model for real-world productivity. Strong at coding and office tasks.

## Overview

- **Provider:** MiniMax
- **Model ID:** `minimax-m2.5`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/minimax-m2.5
- **Version:** M2.5
- **Best for:** Coding (SWE-Bench 80.2%), agentic workflows, office productivity, browsing

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.3 / 1M tokens |
| Output | $1.2 / 1M tokens |
| Cache read | $0.03 / 1M tokens |
| Cache write (5 minutes) | $0.3 / 1M tokens |

## Specifications

- **Context window:** 205K
- **Maximum output:** 197K
- **Released:** 2026-02

## Capabilities

- chat
- tool_use
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "minimax-m2.5"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/minimax-m2.5.