# Qwen3-Coder-480B-A35B-Instruct

> Open-weights Qwen coding model with tool calling, structured output and a 256K-token context window.

## Key facts

- Model author: Qwen
- Input: $1.50 per 1M tokens (starting tier)
- Output: $7.50 per 1M tokens (starting tier)
- Context window: 256,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: structured_output, tools
- Model IDs: `qwen/qwen3-coder-480b-a35b-instruct`
- Model page: https://www.realrelay.ai/model/qwen/qwen3-coder-480b-a35b-instruct

## Overview

Qwen3-Coder-480B-A35B-Instruct is an open-weights coding model from Alibaba Cloud's Qwen3-Coder series. It accepts text input, returns text, supports tool calling and structured output, and has a 256K-token context window for work across many source files. Pricing is tiered and starts at $1.50 per 1M input tokens.

Qwen3-Coder-480B-A35B-Instruct has a 256K-token context window. It accepts text input and returns text. Its model weights are openly available.

## Capabilities

Qwen3-Coder-480B-A35B-Instruct takes text input and returns text, including source code. It supports tool calling and structured output, so a coding agent can have it run commands through tools and receive edits or plans in a parseable format.

The 256K-token context window holds many files, tool results and instructions in one request. The model weights are openly available, so teams can also run the model themselves.

## Pricing

Qwen3-Coder-480B-A35B-Instruct uses tiered pricing per 1M tokens, and the figures shown are for the starting tier: from $1.50 for input and from $7.50 for output.

Qwen3-Coder-480B-A35B-Instruct is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3-Coder-480B-A35B-Instruct for coding agents: it can read files, call tools to run commands or edit code, and return structured output for the next step of an automated workflow.

The 256K-token context window lets a request carry several source files and tool results together, and open weights suit teams that also want to host the model themselves.

## 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-coder-480b-a35b-instruct", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3-Coder-480B-A35B-Instruct?

Qwen3-Coder-480B-A35B-Instruct is an open-weights coding model from Alibaba Cloud's Qwen3-Coder series. It accepts text input, returns text, supports tool calling and structured output, and has a 256K-token context window for work across many source files.

### How much does Qwen3-Coder-480B-A35B-Instruct cost?

Qwen3-Coder-480B-A35B-Instruct has tiered pricing that starts at $1.50 per 1M input tokens and $7.50 per 1M output tokens.

### What is the context window of Qwen3-Coder-480B-A35B-Instruct?

Qwen3-Coder-480B-A35B-Instruct has a 256K-token context window.

### What inputs and outputs does Qwen3-Coder-480B-A35B-Instruct support?

Qwen3-Coder-480B-A35B-Instruct accepts text input and returns text.

### Does Qwen3-Coder-480B-A35B-Instruct support tool calling and structured output?

Yes. Qwen3-Coder-480B-A35B-Instruct supports tool calling and structured output.

### What is Qwen3-Coder-480B-A35B-Instruct used for?

Qwen3-Coder-480B-A35B-Instruct is used for coding agents and code-focused tasks that combine tool calling, structured output and a long context window.

### How do I call Qwen3-Coder-480B-A35B-Instruct through the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3-coder-480b-a35b-instruct.