# Qwen3.6-Flash

> Fast, efficient Alibaba language model that accepts text, image and video input.

## Key facts

- Model author: Qwen
- Input: $0.1714 per 1M tokens (starting tier)
- Output: $1.0286 per 1M tokens (starting tier)
- Cached input: $0.0171 per 1M tokens
- Context window: 1,000,000 tokens
- Maximum output: 64,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-04-27
- Model IDs: `jd/qwen3.6-flash`, `qwen/qwen3.6-flash`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.6-flash

## Overview

Qwen3.6-Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It accepts text, image and video input and returns text, and it adds reasoning, tool calling and structured output, which makes it a light option for agents that need to see.

It has a 1M-token context window and can generate up to 64,000 output tokens. It accepts text, image and video input and returns text. It was released on April 27, 2026.

## Capabilities

Qwen3.6-Flash supports tool calling, reasoning, structured output and vision. It accepts text, image and video input and returns text.

Alibaba documents function calling for the Qwen3.6 series, so the model can act on image or video content, and structured output in non-thinking mode, for example valid JSON from a photo.

## Pricing

Pricing for Qwen3.6-Flash starts from $0.1714 per 1M input tokens and $1.0286 per 1M output tokens, with cache reads from $0.0171 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3.6-Flash is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.6-Flash where response speed and volume matter, such as reading batches of screenshots, photos or short videos and returning structured JSON.

With a 1M-token context window it can also take long documents, and tool calling lets an agent act on what the model reads. It suits batch jobs where each request is small and many run in parallel.

## 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/qwen3.6-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.6-Flash?

Qwen3.6-Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.

### How much does Qwen3.6-Flash cost?

Pricing for Qwen3.6-Flash starts from $0.1714 per 1M input tokens and $1.0286 per 1M output tokens, with cache reads from $0.0171 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

### What is the context window of Qwen3.6-Flash?

Qwen3.6-Flash has a 1M-token context window and can generate up to 64,000 output tokens.

### What inputs and outputs does Qwen3.6-Flash support?

Qwen3.6-Flash accepts text, image and video input and returns text.

### Does Qwen3.6-Flash support tool calling?

Yes. Qwen3.6-Flash supports tool calling, reasoning, structured output and vision.

### When was Qwen3.6-Flash released?

Qwen3.6-Flash was released on April 27, 2026.

### How do I call Qwen3.6-Flash via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3.6-flash to use Qwen3.6-Flash.