Skip to main content
Qwen Image 3.0 is a unified synchronous image model for text-to-image generation and text-guided image editing. Image editing accepts one to three reference images. Each request can return up to six PNG images, and output URLs remain available for 24 hours. Download results before they expire. Use qwen-image-3-0 in the model field. The request waits for completion and returns image URLs in outputs.images.

Model ID

Pass this exact public ID in the top-level model field.

Supported modes

  • text_to_image
  • image_edit

Inputs

  • Text
  • Image

Outputs

  • Image

Capabilities

  • Text-to-image
  • Image editing

Additional capabilities

  • Text-to-image generation
  • Editing with 1-3 reference images
  • Up to 6 outputs
  • Negative prompt
  • Seed control
  • Prompt rewriting
  • Watermark control

Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the API reference overview for authentication, request conventions, and response schemas.