Image model
Wan 2.7 Image Pro
Alibaba Tongyi Wan 2.7 Image Pro — higher-fidelity tier with thinking mode, multi-reference editing, and up to 4K text-to-image output.
wan/wan2.7-image-proAPI
Call Wan 2.7 Image Pro
Every model takes the same request, so switching to Wan 2.7 Image Pro is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What Wan 2.7 Image Pro 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 9 images
Output
- Aspect ratios
- 1:1
- 16:9
- 9:16
- 4:3
- 3:4
- 3:2
- 2:3
Leave out
size, or sendauto, and Mynth picks one for the prompt. Any other ratio snaps to the closest of these. Sizes- 4K
- Yes · any ratio with
_4k, such as16:9_4k
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": 9
}
]
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.075 / image
- Image at 4K
- $0.075 / image
- Input image
- Free
Estimate a request
1 × $0.075
Held when the task is created. Only images that succeed are charged.