# Qwen3-Coder-Flash

> Alibaba's fast, cost-efficient coding agent model for autonomous programming through tool calling.

## Key facts

- Model author: Qwen
- Input: $0.30 per 1M tokens (starting tier)
- Output: $1.50 per 1M tokens (starting tier)
- Cached input: $0.06 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-09-17
- Knowledge cutoff: 2025-06-30
- Model IDs: `qwen/qwen3-coder-flash`
- Model page: https://www.realrelay.ai/model/qwen/qwen3-coder-flash

## Overview

Qwen3-Coder-Flash is a coding agent model from Alibaba, designed for autonomous programming through tool calling. It is built to be fast and cost-efficient, taking text in and returning text, which suits agent loops that send many requests in a row.

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 17, 2025.

## Capabilities

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

Its design centres on autonomous programming: the model works through a coding task by calling the tools you supply and acting on their results, rather than only answering in text.

## Pricing

Pricing for Qwen3-Coder-Flash starts from $0.30 per 1M input tokens and $1.50 per 1M output tokens, with cache reads from $0.06 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3-Coder-Flash is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3-Coder-Flash for coding agents that write, edit and repair code by calling the tools you provide. The 1M-token context window lets an agent keep a large repository and its working history in a single request.

Because it is positioned as fast and cost-efficient, it also suits high-volume programming workloads, such as automated code changes that run many short requests in a loop, with structured output for results that scripts 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-coder-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3-Coder-Flash?

Qwen3-Coder-Flash is a coding agent model from Alibaba, designed for autonomous programming through tool calling.

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

Pricing for Qwen3-Coder-Flash starts from $0.30 per 1M input tokens and $1.50 per 1M output tokens, with cache reads from $0.06 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

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

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

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

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

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

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

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

Qwen3-Coder-Flash was released on September 17, 2025.

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

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