# Qwen3.7-Max

> Flagship text model of Alibaba's Qwen3.7 series, designed for agent-centric workloads, coding and office tasks.

## Key facts

- Model author: Qwen
- Input: $1.7143 per 1M tokens (starting price)
- Output: $5.1429 per 1M tokens (starting price)
- Cached input: $0.50 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-05-21
- Model IDs: `jd/qwen3.7-max`, `qwen/qwen3.7-max`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.7-max

## Overview

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding and in office and productivity tasks. It reads and writes text only, with reasoning, tool calling and structured output for agents that plan and act.

It has a 1M-token context window. It accepts text input and returns text. It was released on May 21, 2026.

## Capabilities

Qwen3.7-Max supports tool calling, reasoning and structured output. It accepts text input and returns text.

The model combines reasoning with tool calling and structured output in a text-only interface, so agents can plan, call tools and return results in a format other software can read.

## Pricing

Pricing for Qwen3.7-Max starts from $1.7143 per 1M input tokens and $5.1429 per 1M output tokens, with cache reads from $0.50 per 1M tokens. Prices vary, so these figures are starting prices. Qwen3.7-Max is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.7-Max for coding agents that plan changes, call tools to edit and test code, and report back in structured output.

For office and productivity work it can draft and revise documents, process long text with its 1M-token context window, and drive multi-step workflows through tool calling. Structured output keeps the results machine-readable.

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

## FAQ

### What is Qwen3.7-Max?

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.

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

Pricing for Qwen3.7-Max starts from $1.7143 per 1M input tokens and $5.1429 per 1M output tokens, with cache reads from $0.50 per 1M tokens. Prices vary, so these figures are starting prices.

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

Qwen3.7-Max has a 1M-token context window.

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

Qwen3.7-Max accepts text input and returns text.

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

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

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

Qwen3.7-Max was released on May 21, 2026.

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

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