# Qwen3.8-Max

> A text-only reasoning model from Alibaba with tool calling and structured output.

## Key facts

- Model author: Qwen
- Input: $2.00 per 1M tokens
- Output: $6.00 per 1M tokens
- Cached input: $0.25 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Model IDs: `qwen/qwen3.8-max`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.8-max

## Overview

Qwen3.8-Max is a reasoning model from Alibaba, served by RealRelay under the model ID qwen/qwen3.8-max. It takes text input and returns text output, and it supports reasoning, structured output and tool calling.

The model reads instructions and returns answers in a single chat response, and it is reached through RealRelay's OpenAI-compatible endpoint.

## Capabilities and modalities

Input and output modality are both text. Supported capabilities are reasoning, structured output and tool calling.

The context window is 1M tokens, which lets a single request carry long prompts, extended source files and lengthy reference material.

Structured output keeps replies in a fixed shape for downstream parsing, and tool calling lets the model request functions that your application exposes.

## Pricing

Input is billed at $2.00 per 1M tokens and output at $6.00 per 1M tokens. Cached input reads are billed at $0.25 per 1M tokens.

Billing is metered on token usage, with input, cached input and output counted separately as shown above.

## Use cases

With a 1M-token context window and text-only modalities, the model fits work that revolves around long written material: reasoning over large prompts, analysing extended source files, and generating structured responses that a program can consume.

Because it supports tool calling, it can also act as the reasoning step of an application that queries its own functions and APIs.

## 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/qwen3.8-max", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.8-Max?

Qwen3.8-Max is a reasoning model from Alibaba that accepts text input, returns text output, and supports structured output and tool calling.

### What are the input and output prices for Qwen3.8-Max?

Input is $2.00 per 1M tokens and output is $6.00 per 1M tokens. Cached input reads are $0.25 per 1M tokens.

### How large is the context window?

The context window is 1M tokens.

### What inputs and outputs does it support?

It accepts text input and produces text output.

### Does Qwen3.8-Max support tool calling and structured output?

Yes. Reasoning, structured output and tool calling are all supported.

### How do I call Qwen3.8-Max through the OpenAI-compatible API?

Send a chat request to RealRelay's OpenAI-compatible endpoint with the model ID qwen/qwen3.8-max; the request and response follow the OpenAI chat format.