Z-Image-Turbo
Z-Image-Turbo Image Generation
- Asynchronous processing mode, returns task ID for subsequent queries
- Lightweight and fast image generation, supports Chinese and English
- Supports 1K/2K resolution tiers, supports smart prompt rewriting
POST
Supported Models
Authorizations
string
required
All endpoints require Bearer Token authenticationGet API Key:Visit API Key Management to get your API KeyAdd to request header:
Body
string
required
Model name
z-image-turbo- Lightweight and fast image generation, supports Chinese and English
string
required
Text description for image generation, up to 800 characters
string
default:"1:1"
Image aspect ratioSupported aspect ratios:
1:1- Square (default)4:3- Landscape 4:33:4- Portrait 3:416:9- Landscape widescreen9:16- Portrait vertical3:2- Landscape 3:22:3- Portrait 2:3
string
default:"1K"
Resolution tier
1K- Standard resolution (default)2K- High definition resolution
boolean
default:"false"
Smart prompt rewritingWhen enabled, AI will automatically optimize the prompt for better results, and costs will increase.
false- Disabled (default)true- Enabled
Resolution Reference Table
Output size is controlled by the combination ofsize (ratio) + resolution (resolution tier).
Usage Examples
Basic Text-to-Image (minimal request)Response
integer
Response status code
array
Response data array
Notes
- Asynchronous Processing: After submission, a
task_idis returned. Poll/v1/tasks/{task_id}to get results - Image Storage: Generated images are mirrored to platform CDN and are valid long-term
- Billing Rules: Billed per successfully generated image, no charge for failures
- Fixed Count: Z-Image-Turbo generates exactly 1 image per request,
nparameter is not supported