# Qwen-Flash

> Qwen text model with reasoning, tool calling and structured output over a 1M-token context window.

## Key facts

- Model author: Qwen
- Input: $0.05 per 1M tokens (starting tier)
- Output: $0.40 per 1M tokens (starting tier)
- Cached input: $0.01 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Model IDs: `qwen/qwen-flash`
- Model page: https://www.realrelay.ai/model/qwen/qwen-flash

## Overview

Qwen-Flash is a text model from Alibaba Cloud's Qwen family that supports reasoning, tool calling and structured output. It takes text input and returns text, and its 1M-token context window lets a single request carry long documents or extended conversations. Pricing is tiered and starts at $0.05 per 1M input tokens.

Qwen-Flash has a 1M-token context window. It accepts text input and returns text.

## Capabilities

Qwen-Flash handles text in and text out. It supports reasoning, tool calling and structured output, so an application can let the model call functions and receive replies in a format that downstream code can parse.

The 1M-token context window suits requests that bundle long source material, such as full documents, logs or multi-turn histories, together with the instruction in one call.

## Pricing

Qwen-Flash uses tiered pricing per 1M tokens, and the figures shown are for the starting tier: from $0.05 for input and from $0.40 for output, and from $0.01 for cached input.

Qwen-Flash is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen-Flash for tool-calling assistants and automation: the model can decide when to call a function, and structured output keeps its answers machine-readable for the next step in a workflow.

Its 1M-token context window also fits long-document tasks such as summarizing or answering questions over large text, with reasoning available for multi-step questions.

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

## FAQ

### What is Qwen-Flash?

Qwen-Flash is a text model from Alibaba Cloud's Qwen family that supports reasoning, tool calling and structured output. It takes text input and returns text, and its 1M-token context window lets a single request carry long documents or extended conversations.

### How much does Qwen-Flash cost?

Qwen-Flash has tiered pricing that starts at $0.05 per 1M input tokens and $0.40 per 1M output tokens, with cached input from $0.01 per 1M tokens.

### What is the context window of Qwen-Flash?

Qwen-Flash has a 1M-token context window.

### What inputs and outputs does Qwen-Flash support?

Qwen-Flash accepts text input and returns text.

### Does Qwen-Flash support tool calling and structured output?

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

### What is Qwen-Flash used for?

Qwen-Flash is used for tool-calling assistants, structured data extraction and question answering over long text, backed by reasoning, structured output and a 1M-token context window.

### How do I call Qwen-Flash through the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen-flash.