# Qwen-Plus

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

## Key facts

- Model author: Qwen
- Input: $0.40 per 1M tokens (starting tier)
- Output: $1.20 per 1M tokens (starting tier)
- Cached input: $0.08 per 1M tokens
- Context window: 1,000,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-02-01
- Knowledge cutoff: 2025-03-31
- Model IDs: `qwen/qwen-plus`
- Model page: https://www.realrelay.ai/model/qwen/qwen-plus

## Overview

Qwen-Plus is a text model from Alibaba Cloud's Qwen family, positioned as a balance of performance, speed and price. It supports reasoning, tool calling and structured output, accepts text input, returns text and offers a 1M-token context window. Pricing is tiered and starts at $0.40 per 1M input tokens.

Qwen-Plus has a 1M-token context window. It accepts text input and returns text. It was released on February 1, 2025.

## Capabilities

Qwen-Plus accepts text and returns text. It supports reasoning, tool calling and structured output, so it can work through multi-step questions, call functions and reply in a format that downstream code can parse.

Its catalog description presents it as a balance of performance, speed and price, and the 1M-token context window lets long inputs go into one request.

## Pricing

Qwen-Plus uses tiered pricing per 1M tokens, and the figures shown are for the starting tier: from $0.40 for input and from $1.20 for output, and from $0.08 for cached input.

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

## Use cases

Use Qwen-Plus for general-purpose text assistants that call tools and return structured replies, such as support agents, internal question answering or workflow automation, where a balance of quality, speed and price matters.

Its 1M-token context window also allows long reports, contracts or conversation histories to go into one request, 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-plus", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen-Plus?

Qwen-Plus is a text model from Alibaba Cloud's Qwen family, positioned as a balance of performance, speed and price. It supports reasoning, tool calling and structured output, accepts text input, returns text and offers a 1M-token context window.

### How much does Qwen-Plus cost?

Qwen-Plus has tiered pricing that starts at $0.40 per 1M input tokens and $1.20 per 1M output tokens, with cached input from $0.08 per 1M tokens.

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

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

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

Qwen-Plus accepts text input and returns text.

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

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

### When was Qwen-Plus released?

Qwen-Plus was released on February 1, 2025.

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

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