# Qwen3-Coder-Plus

> Alibaba's proprietary coding agent model, specializing in autonomous programming via tool calling.

## Key facts

- Model author: Qwen
- Input: $1.00 per 1M tokens (starting tier)
- Output: $5.00 per 1M tokens (starting tier)
- Cached input: $0.20 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-09-23
- Knowledge cutoff: 2025-06-30
- Model IDs: `qwen/qwen3-coder-plus`
- Model page: https://www.realrelay.ai/model/qwen/qwen3-coder-plus

## Overview

Qwen3-Coder-Plus is a proprietary coding agent model from Alibaba that specializes in autonomous programming via tool calling. It reads text and returns text, with reasoning and structured output available alongside tool calls, and it is built to carry multi-step programming tasks through on its own.

It has a 1M-token context window. It accepts text input and returns text. Its knowledge cutoff is June 30, 2025 and it was released on September 23, 2025.

## Capabilities

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

Tool calling is central to the model: it plans programming work, invokes the tools you define and iterates on their output, so a single agent run can span several rounds of reading, editing and checking code.

## Pricing

Pricing for Qwen3-Coder-Plus starts from $1.00 per 1M input tokens and $5.00 per 1M output tokens, with cache reads from $0.20 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3-Coder-Plus is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3-Coder-Plus for autonomous coding agents that implement features, fix bugs and refactor code by calling the tools you expose.

The 1M-token context window lets an agent load a large repository, its tests and its task history together, and structured output gives downstream tooling results it can parse reliably. Reasoning helps it work through multi-step bugs.

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

## FAQ

### What is Qwen3-Coder-Plus?

Qwen3-Coder-Plus is a proprietary coding agent model from Alibaba that specializes in autonomous programming via tool calling.

### How much does Qwen3-Coder-Plus cost?

Pricing for Qwen3-Coder-Plus starts from $1.00 per 1M input tokens and $5.00 per 1M output tokens, with cache reads from $0.20 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

### What is the context window of Qwen3-Coder-Plus?

Qwen3-Coder-Plus has a 1M-token context window.

### What inputs and outputs does Qwen3-Coder-Plus support?

Qwen3-Coder-Plus accepts text input and returns text.

### Does Qwen3-Coder-Plus support tool calling?

Yes. Qwen3-Coder-Plus supports tool calling, reasoning and structured output.

### When was Qwen3-Coder-Plus released?

Qwen3-Coder-Plus was released on September 23, 2025.

### How do I call Qwen3-Coder-Plus via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3-coder-plus to use Qwen3-Coder-Plus.