Image model
MOSS-Image
OpenMOSS MOSS-Image is a 5B single-stream DiT text-to-image model, fine-tuned for Chinese and English text rendering and JSON layout prompts that place text and objects.
openmoss-team/moss-imageAPI
Call MOSS-Image
Every model takes the same request, so switching to MOSS-Image is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What MOSS-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
Output
- Aspect ratios
- 1:1
- 2:3
- 3:2
- 3:4
- 4:3
- 9:16
- 16:9
- 1:2
- 2:1
- 1:3
- 3:1
- 1:4
- 4:1
- 1:8
- 8:1
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": {}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.055 / image
Estimate a request
1 × $0.055
Held when the task is created. Only images that succeed are charged.