# Qwen3.7-Flash

Qwen 3.7 Flash - vision-language model positioned for multimodal applications including visual coding, object recognition, and computer interaction tasks.

## Overview

- **Provider:** Qwen
- **Model ID:** `qwen3.7-flash`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/qwen3.7-flash
- **Version:** 3.7 Flash
- **Best for:** Quick multimodal responses, visual coding, computer-use tasks, cost-sensitive workloads

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.03 / 1M tokens |
| Output | $0.13 / 1M tokens |
| Cache read | $0.006 / 1M tokens |
| Cache write (5 minutes) | $0.0375 / 1M tokens |

## Specifications

- **Context window:** 1M
- **Maximum output:** 66K
- **Typical latency:** 8 ms
- **Released:** 2026-07

## Capabilities

- chat

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "qwen3.7-flash"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/qwen3.7-flash.