# Qwen3.8-Max (0902)

> Dated Alibaba snapshot with the 0902 suffix, accepting text, image and video input.

## Key facts

- Model author: Qwen
- Input: $2.00 per 1M tokens
- Output: $6.00 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-09-02
- Model IDs: `qwen/qwen3.8-max-0902`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.8-max-0902

## Overview

Qwen3.8-Max (0902) is a dated snapshot from Alibaba's Qwen team, identified by the 0902 suffix. It accepts text, image and video input and returns text, with reasoning, tool calling and structured output. Its dated identifier makes it a stable target for applications that need the same model behaviour from one request to the next.

It has a 1M-token context window. It accepts text, image and video input and returns text. It was released on September 2, 2026.

## Capabilities

Qwen3.8-Max (0902) supports tool calling, reasoning, structured output and vision. It accepts text, image and video input and returns text.

Because it is a fixed dated snapshot, the 0902 identifier keeps pointing to the same release, which helps when you want repeatable behaviour. It supports vision as well as text, so images and video can be part of a request, and structured output lets other systems parse the result.

## Pricing

Qwen3.8-Max (0902) costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. Qwen3.8-Max (0902) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.8-Max (0902) when an agent needs to read screenshots, photos or video, reason about them and call tools, and you want the model version to stay fixed.

It also suits long-context text work, since the 1M-token window can hold large documents, with structured output for results that other systems can parse.

## 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-0902", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) is a dated snapshot from Alibaba's Qwen team, identified by the 0902 suffix.

### How much does Qwen3.8-Max (0902) cost?

Qwen3.8-Max (0902) costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

### What is the context window of Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) has a 1M-token context window.

### What inputs and outputs does Qwen3.8-Max (0902) support?

Qwen3.8-Max (0902) accepts text, image and video input and returns text.

### Does Qwen3.8-Max (0902) support tool calling?

Yes. Qwen3.8-Max (0902) supports tool calling, reasoning, structured output and vision.

### When was Qwen3.8-Max (0902) released?

Qwen3.8-Max (0902) was released on September 2, 2026.

### How do I call Qwen3.8-Max (0902) via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3.8-max-0902 to use Qwen3.8-Max (0902).