# MiMo V2.5 Pro

Best base pricing among frontier models. 1.02T total, 42B active (MoE with hybrid-attention). Surpasses GPT-5.5 on SWE-Bench Pro.

## Overview

- **Provider:** Xiaomi
- **Model ID:** `mimo-v2.5-pro`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/mimo-v2.5-pro
- **Version:** V2.5 Pro
- **Best for:** Complex software engineering, autonomous agents, large codebase reasoning, frontier-level coding

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.435 / 1M tokens |
| Output | $0.87 / 1M tokens |
| Cache read | $0.0036 / 1M tokens |
| Cache write (5 minutes) | $0.435 / 1M tokens |

## Specifications

- **Context window:** 1.05M
- **Maximum output:** 131K
- **Typical latency:** 18 ms
- **Released:** 2026-04-22

## Capabilities

- chat
- tool_use
- reasoning
- coding
- analysis

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "mimo-v2.5-pro"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/mimo-v2.5-pro.