Image model
FLUX.3
FLUX.3 is Black Forest Labs’ image model for text-to-image, precise local edits, and multi-reference composition, with native 4K output and stronger typography.
black-forest-labs/flux-3API
Call FLUX.3
Every model takes the same request, so switching to FLUX.3 is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What FLUX.3 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 10 images
Output
- Aspect ratios
- 21:9
- 2:1
- 16:9
- 3:2
- 4:3
- 5:4
- 1:1
- 4:5
- 3:4
- 2:3
- 9:16
- 1:2
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": 10
}
]
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.10 / image
- Image at 4K
- $0.61 / image
- Input image
- Free
Estimate a request
1 × $0.10
Held when the task is created. Only images that succeed are charged.