Live APIQwen Image

Qwen Image 3

qwen-image-3

High-fidelity text-to-image and image-to-image generation with strong typography, layout, and multilingual prompt following.

View request Docs

Model overview

Endpoint: /api/v1/images/generations
Credit cost: 10 credits / image
Typical latency: 20-60 sec
Input and output: Text, up to 3 images → PNG or JPEG

Capabilities

1K and 2K output
Text and image conditioning
Prompt expansion
Deterministic seeds

Request parameters

Parameter	Type	Requirement	Description
model	string	Required	Model identifier. Default: `qwen-image-3`
prompt	string	Required	Generation prompt, up to 800 characters.
image_urls	string[]	Optional	Up to three public image URLs for image-to-image generation.
aspect_ratio	string	Optional	Output aspect ratio. Default: `16:9`
resolution	1K \| 2K	Optional	Output resolution tier. Default: `1K`
output_format	png \| jpeg	Optional	Generated file format. Default: `png`
seed	integer	Optional	Integer from 0 to 2147483647. Default: `1`

Request example

curl https://qwenapi.org/api/v1/images/generations \
  -H "Authorization: Bearer $QWEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-3",
  "prompt": "Editorial product photo of a translucent blue speaker on a steel desk, soft morning light",
  "aspect_ratio": "16:9",
  "resolution": "1K",
  "output_format": "png"
}'

The generation endpoint is asynchronous. Poll GET /api/v1/tasks/ with the same Bearer key.