# MiMo-V2.6 Flash

## Best for

Low-cost omnimodal work across text, images, audio, and video

## When not to use

The hardest long-horizon agent tasks — MiMo-V2.6 Pro is the stronger model for a main coding agent.

## Overview

MiMo-V2.6-Flash is the smaller sibling of MiMo-V2.6-Pro: a 309B-parameter mixture-of-experts with 15B active, using hybrid sliding-window and global attention to keep long prompts cheap. It has vision and audio encoders, understands video, and has a 1,048,576-token context window.

| | |
| --- | --- |
| API identifier | `mimo-v2.6-flash` |
| 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 |
| --- | --- | --- |
| $0.14 | $0 | $0.28 |

## Call it

Put `mimo-v2.6-flash` 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-flash",
    "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).