# Qwen3.7-Plus

> Cost-effective Alibaba model that reads image, text and video input and returns text.

## Key facts

- Model author: Qwen
- Input: $0.2857 per 1M tokens (starting tier)
- Output: $1.1429 per 1M tokens (starting tier)
- Cached input: $0.0571 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: 2026-06-03
- Model IDs: `jd/qwen3.7-plus`, `qwen/qwen3.7-plus`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.7-plus

## Overview

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It accepts image, text and video input and returns text, and it adds reasoning, tool calling and structured output for applications that need to see as well as read. Alibaba also recommends it for general text extraction from images.

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 June 3, 2026.

## Capabilities

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

Alibaba documents function calling that acts on image or video content, and structured output in non-thinking mode, for example extracting product details from a photo as valid JSON. Alibaba also recommends this model for general text extraction from images.

## Pricing

Pricing for Qwen3.7-Plus starts from $0.2857 per 1M input tokens and $1.1429 per 1M output tokens, with cache reads from $0.0571 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3.7-Plus is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.7-Plus for general text extraction from images and for turning product photos or screenshots into JSON that downstream systems can parse.

With a 1M-token context window and tool calling, it also suits agents that read long documents or video, reason about them and call tools to act. Structured output helps when results feed a database or another program.

## 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-plus", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.7-Plus?

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

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

Pricing for Qwen3.7-Plus starts from $0.2857 per 1M input tokens and $1.1429 per 1M output tokens, with cache reads from $0.0571 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

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

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

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

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

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

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

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

Qwen3.7-Plus was released on June 3, 2026.

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

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