Z-Image Turbo
Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
- Price
- $0.05 each2 credits each
- Model id
z-image-turbo- Output
- Image
API keys come with the Scale and Ultra plans

Run it
The smallest request that works: the required fields only.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "z-image-turbo",
"input": {
"prompt": "A hyper-realistic, close-up portrait of a tribal elder from the Omo Valley, painted wit..."
}
}'- EstimatePOST /estimate with the same body returns the price and charges nothing.
- RunPOST /run returns an id at once, with status processing.
- CollectGET /generations/{id}?wait=55 returns the file URLs, or pass a webhook.
Parameters
17 fields in input, required first.
- string
promptRequiredText prompt for image generation
- integerDefault 1024
heightOptionalHeight of the generated image
- integerDefault 1024
widthOptionalWidth of the generated image
- integerDefault 8
num_inference_stepsOptionalNumber of inference steps.
- numberDefault 0
guidance_scaleOptionalGuidance scale. Should be 0 for Turbo models
- integer
seedOptionalRandom seed. Set for reproducible generation
- booleanDefault false
go_fastOptionalUnused compatibility field; this endpoint always runs the bf16 model.
- png, jpg, webpDefault jpg
output_formatOptionalFormat of the output images
- integerDefault 80
output_qualityOptionalQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for.png outputs
- integerDefault 1
num_outputsOptionalNumber of output images to generate (currently only 1 is supported).
- integerDefault 2
safety_toleranceOptionalUnused compatibility field for Flux-style clients; this model has no safety checker.
- string
model_versionOptionalUnused compatibility field; this endpoint always runs Z-Image-Turbo.
- string
negative_promptOptionalUnused compatibility field; Z-Image-Turbo is guidance-free (guidance_scale=0) and does not use negative prompts.
- string
aspect_ratioOptionalUnused compatibility field; set width/height directly instead.
- string
megapixelsOptionalUnused compatibility field; set width/height directly instead.
- booleanDefault true
disable_safety_checkerOptionalUnused compatibility field; this model has no safety checker.
- booleanDefault false
enable_safety_checkerOptionalUnused compatibility field; this model has no safety checker.
More text to image models
from $0.10GPT Image 2
OpenAI image generation: excellent prompt-following and clean text rendering; takes reference images.
from $0.05GPT Image 2.5 Flare
Generates images from a text prompt, with five quality tiers up to 4K and strong in-image typography.
from $0.05GPT Image 2.5 Sunburst
Generates images from a text prompt, with five quality tiers up to 4K and strong in-image typography.
$0.05Flux Schnell
The fastest image generation model tailored for local development and personal use
