# MiMo-V2.6 Pro

## Best for

A frontier open-weight agent that reads text, images, audio, and video

## When not to use

High-volume or latency-sensitive steps — use MiMo-V2.6 Flash for sub-agents and bulk work.

## Overview

MiMo-V2.6-Pro is Xiaomi's flagship open-weight model: a 1.02T-parameter mixture-of-experts with 42B active per token. It is natively omnimodal, taking text, images, audio, and video in one model, and its 1,048,576-token context window fits long repositories, tool traces, and multi-session agent runs.

| | |
| --- | --- |
| API identifier | `mimo-v2.6-pro` |
| Developer | Xiaomi |
| Context window | 1,048,576 tokens |
| Supports | text, reasoning, tool-use, image input, vision, audio input, video input |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.44 | $0 | $0.87 |

## Call it

Put `mimo-v2.6-pro` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2.6-pro",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).