Get API Key Get API
Docs

Qwen Image 3.0 Image Generation

- Asynchronous processing mode, returns a task ID for subsequent queries

  • Supports text-to-image and image-to-image (1-3 reference images for editing)
  • Supports 1K / 2K resolution, up to 6 images per request
  • Standard and Pro variants (Pro is stronger for dense layout and text)

Request example

curl --request POST \
  --url https://api.openveer.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen-image-3.0",
    "prompt": "A cafe poster with the title Autumn Limited, warm tones, refined layout",
    "size": "16:9",
    "resolution": "1K"
  }'

Response example

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JGXYZ1234567890ABCDEF"
    }
  ]
}

Supported Models

Model Description Max images Resolution
qwen-image-3.0 Clear instruction following, stable text rendering; better value for general use 6 1K / 2K
qwen-image-3.0-pro Richer content; best for newspapers, storyboards, menus, exams, dense layout 6 1K / 2K
Tip

Prefer -pro for dense text/layout. Use qwen-image-3.0 for general images. Prompt max \~4.5k tokens. Model names are not interchangeable with the 2.0 series.

Authorizations

Authorization string

All endpoints require Bearer Token authentication

Get your API Key from the API Key Management Page:

Authorization: Bearer YOUR_API_KEY

Body

model string

Model name

  • qwen-image-3.0 - Standard
  • qwen-image-3.0-pro - Pro (dense text / layout)
nsfw_check boolean

Whether to run content moderation before submitting the image task.

  • true: use omni-moderation-latest to review prompts and input images
  • false or omitted: do not send a moderation request, adding no moderation cost or latency (default)
prompt string

Text description for image generation, max \~4.5k tokens

image_urls string[]

Reference image URL array (image-to-image / editing), 1-3 images

  • Public http(s):// URL or data:image/png;base64,... (base64 is re-uploaded first)
  • Formats: JPG / JPEG / PNG / BMP / TIFF / WEBP / GIF
  • Per file ≤ 10MB; width/height recommended 384-2048 px
resolution string

Resolution tier (affects billing tier)

  • 1K (default; lowercase accepted)
  • 2K

You may skip the tier and pass pixels in size (e.g. 1600x900). With raw pixels, area > 2.25M pixels bills as 2K.

size string

Aspect ratio, or explicit pixel size

Supported ratios:

  • 1:1 (default)
  • 4:3 / 3:4
  • 16:9 / 9:16
  • 3:2 / 2:3

Also accepts 16x9 style, or pixels like 1024x1024. For custom pixels, each edge (width and height) must be 512–2048, aspect ratio 1:8 \~ 8:1.

If neither size nor resolution is set, output is fixed at 1024×1024.

n integer

Number of images, 1-6. Values above 6 are clamped to 6.

negative_prompt string

Negative prompt: content to avoid

prompt_extend boolean

Intelligent prompt rewriting

Defaults to off for predictable results. Set to true to enable intelligent rewriting.

prompt_extend_mode string

Rewrite mode (3.0 series only; requires prompt_extend: true)

  • direct - works for text-to-image and image-to-image
  • agent - text-to-image only, more aggressive rewrite

Invalid values are ignored.

Size Reference Table

Combine resolution (tier) + size (ratio):

Resolution 1:1 4:3 3:4 16:9 9:16 3:2 2:3
1K 1024×1024 1152×864 864×1152 1280×720 720×1280 1248×832 832×1248
2K 2048×2048 2048×1536 1536×2048 2048×1152 1152×2048 2048×1360 1360×2048

Use Cases

Text-to-image (multiple)

{
  "model": "qwen-image-3.0",
  "prompt": "Flat illustration of a city skyline at dusk, warm orange tones",
  "size": "16:9",
  "resolution": "1K",
  "n": 4
}

Dense layout with rewrite

{
  "model": "qwen-image-3.0-pro",
  "prompt": "A Western restaurant menu with appetizers, mains, and desserts columns, five dishes each with prices, serif font, cream background",
  "size": "3:4",
  "resolution": "2K",
  "prompt_extend": true,
  "prompt_extend_mode": "agent"
}

Image-to-image (edit)

{
  "model": "qwen-image-3.0-pro",
  "prompt": "Change the sign text to Open, keep everything else the same",
  "image_urls": ["https://example.com/shop.jpg"],
  "size": "1:1"
}

Negative prompt

{
  "model": "qwen-image-3.0",
  "prompt": "Photorealistic mountain cabin in morning mist",
  "negative_prompt": "text, watermark, people, low resolution",
  "size": "3:2"
}

Limits

Item Limit
Prompt ≤ 4.5k tokens
Output size Custom pixels: each edge 512–2048; aspect 1:8 \~ 8:1
Image count 1-6 (excess clamped)
Reference images 1-3
Reference formats JPG / JPEG / PNG / BMP / TIFF / WEBP / GIF
Reference size ≤ 10MB; width/height recommended 384-2048 px

Response

code integer

Status code; 200 on success

data array
Response data array
status string

Task status; submitted on create

task_id string

Task ID for polling results

Differences from 2.0

2.0 series 3.0 series
Prompt length Shorter \~4.5k tokens
prompt_extend_mode Not supported direct / agent
Resolution 1K / 2K 1K / 2K (Pro 2K costs more)
Reference images Supported 1-3 images

Notes

  1. Async: Submit returns a task_id. Poll Get Task Status every 3\~5 seconds; client timeout \~3 minutes (2K + multi-image is slower).
  2. Storage: Generated images are mirrored to the platform CDN and remain available long-term.
  3. Billing: Per delivered image × resolution tier by actual pixel area (> 2.25M pixels = 2K). qwen-image-3.0 charges the same for 1K/2K; -pro 2K is 2× 1K. Failures are fully refunded; reference images are free.
  4. Errors: Custom size edge outside 512–2048, invalid ratio, agent on image-to-image, unreachable/oversized references → 400; rate limit → 429.
Note

Query results

Use Get Task Status for progress and result.images.

This documentation is built and hosted on Mintlify, a developer documentation platform.