# Qwen3.8 Flash

## Best for

Quick image analysis with a million-token context

## When not to use

Audio input. Not the pick for frontier-scale coding; this is the compact visual Qwen, not Kimi K3 or a DeepSeek Pro main agent.

## Overview

Qwen3.8-27B is a compact model that works with text and images. Its 1,000,000-token context window is useful for visual tasks with a lot of supporting material, and it runs on a single H100 instance.

| | |
| --- | --- |
| API identifier | `qwen3.8-flash` |
| Developer | Qwen |
| Context window | 1,000,000 tokens |
| Supports | text, reasoning, tool-use, image input, vision |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.15 | $0.02 | $0.47 |

## Call it

Put `qwen3.8-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": "qwen3.8-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).