API docs / Image models

Qwen Image 3 (Text to image) API

Create an image with dense English or Chinese text using Qwen Image 3.

Model id
alibaba/qwen-image-3/text-to-image
Provider
Qwen
Output
Image
Price
From 14 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "alibaba/qwen-image-3/text-to-image". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "alibaba/qwen-image-3/text-to-image",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Up to 5000 characters

reference_imagesarray of URLs

1 to 3 JPEG, PNG or WebP images, 384 to 2048 px per side and up to 10 MB each. Refer to them as image 1, image 2 and image 3.

Up to 3 files · Accepts image/*

aspect_ratiostring

Default: 1:1

One of: 1:1, 4:3, 3:4, 16:9, 9:16

resolutionstring

1K is up to 1024 px on the long side; 2K is up to 2048 px.

Default: 1k

One of: 1k, 2k

enhance_promptboolean

Let the model rewrite the prompt. Turn it off when every word of visible text must stay exactly as written.

Default: true

negative_promptstring

Default:

Up to 500 characters