# Qwen-Max

> Qwen text model with tool calling and structured output and a 128K-token context window.

## Key facts

- Model author: Qwen
- Input: $1.60 per 1M tokens
- Output: $6.40 per 1M tokens
- Cached input: $0.32 per 1M tokens
- Context window: 128,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: structured_output, tools
- Model IDs: `qwen/qwen-max`
- Model page: https://www.realrelay.ai/model/qwen/qwen-max

## Overview

Qwen-Max is a text model from Alibaba Cloud's Qwen family that supports tool calling and structured output. It takes text input, returns text and has a 128K-token context window. It is priced at $1.60 per 1M input tokens and $6.40 per 1M output tokens, with cached input at $0.32 per 1M tokens.

Qwen-Max has a 128K-token context window. It accepts text input and returns text.

## Capabilities

Qwen-Max accepts text input and returns text. It supports tool calling and structured output, so an application can have the model call external functions and return replies in a fixed format.

The 128K-token context window holds long documents or extended conversation histories in a single request, and cached input is billed at a lower rate when the same prompt prefix repeats.

## Pricing

Qwen-Max is priced per 1M tokens at $1.60 for input and $6.40 for output, with cached input at $0.32.

Qwen-Max is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen-Max for assistants that call external tools and must return replies in a fixed structure, for example filling forms, producing JSON for an API or routing requests between services.

The 128K-token window fits long documents and conversation histories in one request, and the lower cached-input rate helps when the same instructions are reused across many calls.

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

## FAQ

### What is Qwen-Max?

Qwen-Max is a text model from Alibaba Cloud's Qwen family that supports tool calling and structured output. It takes text input, returns text and has a 128K-token context window.

### How much does Qwen-Max cost?

Qwen-Max costs $1.60 per 1M input tokens and $6.40 per 1M output tokens, and cached input is $0.32 per 1M tokens.

### What is the context window of Qwen-Max?

Qwen-Max has a 128K-token context window.

### What inputs and outputs does Qwen-Max support?

Qwen-Max accepts text input and returns text.

### Does Qwen-Max support tool calling and structured output?

Yes. Qwen-Max supports tool calling and structured output.

### What is Qwen-Max used for?

Qwen-Max is used for tool-calling assistants and structured-output tasks over text, such as form filling, JSON generation and request routing.

### How do I call Qwen-Max through the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen-max.