API docs / Image models

Z-Image Turbo API

Generates photorealistic images from text prompts using a fast 6 billion parameter model optimized by PrunaAI. Produces high-quality images in sub-second generation time with only 8 inference steps. Excels at creating realistic photographs, portraits, and scenes with natural lighting and textures. Features exceptional text rendering capabilities for both English and Chinese characters, making it ideal for generating images with signs, labels, posters, and other text elements. Optimized through PrunaAI's compression engine using caching, compilation, and quantization techniques for maximum speed while maintaining quality. Best suited for rapid prototyping, cost-effective generation at scale, and applications requiring quick iterations.

Model id
prunaai/z-image-turbo
Provider
Z Image
Output
Image
Price
From 8 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": "prunaai/z-image-turbo". 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": "prunaai/z-image-turbo",
  "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

Text prompt for image generation

seednumber

Random seed. Set for reproducible generation

guidancenumber

Guidance scale. Should be 0 for Turbo models

Default: 0

Min 0 · Max 20

stepsnumber

Number of inference steps.

Default: 8

Min 1 · Max 50

output_formatstring

Default: jpg

One of: png, jpg, webp

go_fastboolean

Apply additional optimizations for faster generation

Default: false

heightnumber

Height of the generated image

Default: 1024

Min 64 · Max 2048

output_qualitynumber

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

Min 0 · Max 100

widthnumber

Width of the generated image

Default: 1024

Min 64 · Max 2048