Image model
MiniMax H3
MiniMax H3 is an open-weights cinema-grade image model for photoreal text-to-image and identity-preserving edits from up to 9 references, at native 1K or 2K.
minimax/h3API
Call MiniMax H3
Every model takes the same request, so switching to MiniMax H3 is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What MiniMax H3 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
- 1–9 images · required
- The model picks its own output size
Output
- Aspect ratios
- 1:1
- 1:2
- 2:1
- 1:3
- 3:1
- 2:3
- 3:2
- 3:4
- 4:3
- 4:5
- 5:4
- 9:16
- 16:9
- 9:21
- 21:9
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",
"min": 1,
"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
- $0.06 / image
- Input image
- $0.03 / input
An input is charged once for every image it goes into: two inputs on four images are eight input charges.
Estimate a request
1 × $0.06
Held when the task is created. Only images that succeed are charged.