# Qwen3.7-Flash

> Alibaba vision-language reasoning model for multimodal agents, visual coding, search and computer interaction.

## Key facts

- Model author: Qwen
- Input: $0.03 per 1M tokens (starting tier)
- Output: $0.13 per 1M tokens (starting tier)
- Cached input: $0.006 per 1M tokens
- Context window: 1,000,000 tokens
- Maximum output: 64,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-07-27
- Model IDs: `qwen/qwen3.7-flash`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.7-flash

## Overview

Qwen3.7-Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search and computer interaction, with strengths in object recognition and spatial understanding, and it takes image, text and video input and returns text, with tool calling and structured output available.

It has a 1M-token context window and can generate up to 64,000 output tokens. It accepts text, image and video input and returns text. It was released on July 27, 2026.

## Capabilities

Qwen3.7-Flash supports tool calling, reasoning, structured output and vision. It accepts text, image and video input and returns text.

Beyond the basic modalities, Alibaba points to object recognition and spatial understanding as strengths. Function calling can act on image or video content, and Alibaba also recommends this model for general text extraction from images.

## Pricing

Pricing for Qwen3.7-Flash starts from $0.03 per 1M input tokens and $0.13 per 1M output tokens, with cache reads from $0.006 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3.7-Flash is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.7-Flash for multimodal agents that interpret what is on a screen and decide what to do next, including computer interaction and visual coding tasks.

It also fits general text extraction from images, search-style questions that mix text with pictures, and object or layout questions that depend on recognition and spatial understanding.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen/qwen3.7-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.7-Flash?

Qwen3.7-Flash is a vision-language reasoning model from Alibaba.

### How much does Qwen3.7-Flash cost?

Pricing for Qwen3.7-Flash starts from $0.03 per 1M input tokens and $0.13 per 1M output tokens, with cache reads from $0.006 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

### What is the context window of Qwen3.7-Flash?

Qwen3.7-Flash has a 1M-token context window and can generate up to 64,000 output tokens.

### What inputs and outputs does Qwen3.7-Flash support?

Qwen3.7-Flash accepts text, image and video input and returns text.

### Does Qwen3.7-Flash support tool calling?

Yes. Qwen3.7-Flash supports tool calling, reasoning, structured output and vision.

### When was Qwen3.7-Flash released?

Qwen3.7-Flash was released on July 27, 2026.

### How do I call Qwen3.7-Flash via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3.7-flash to use Qwen3.7-Flash.