Image model
Z-Image
Tongyi-MAI Z-Image is a 6B single-stream DiT foundation model for high-quality text-to-image generation with strong style coverage and prompt adherence.
tongyi-mai/z-imageAPI
Call Z-Image
Every model takes the same request, so switching to Z-Image is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What Z-Image accepts
Read from the same registry the API validates against. A request outside it is refused when the task is created, before anything is charged.
Modes and inputs
- Text → Image
- Prompt only
- Image → Image
- Up to 1 image
Output
- Aspect ratios
- 1:1
- 9:7
- 7:9
- 4:3
- 3:4
- 3:2
- 2:3
- 16:9
- 9:16
- 21:9
- 9:21
Leave out
size, or sendauto, and Mynth picks one for the prompt. Any other ratio snaps to the closest of these. Sizes- 4K
- No. A 4k size fails the task
Prompt
- Negative prompt
- Not supported. Dropped before the provider call, no error
The contract as GET /models returns it
{
"modes": {
"txt->img": {},
"img->img": {
"inputs": {
"rules": [
{
"type": "image",
"max": 1
}
]
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.02 / image
- Input image
- Free
Estimate a request
1 × $0.02
Held when the task is created. Only images that succeed are charged.