Image model
FLUX.2 Klein
FLUX.2 [klein] 4B is a step-distilled open-weight model for sub-second text-to-image and multi-reference editing, designed for consumer GPUs under Apache 2.0.
black-forest-labs/flux.2-klein-4bAPI
Call FLUX.2 Klein
Every model takes the same request, so switching to FLUX.2 Klein is a change to the model field. These samples are written for its own contract and send as they are.
Specifications
What FLUX.2 Klein 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 4 images
Output
- Aspect ratios
- 3:2
- 2:3
- 16:9
- 9:16
- 1:1
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": {},
"img->img": {
"inputs": {
"rules": [
{
"type": "image",
"max": 4
}
]
}
}
}
}Pricing
What it costs
Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works
Rates
- Image
- $0.001 / image
- Input image
- Free
Estimate a request
1 × $0.001
Held when the task is created. Only images that succeed are charged.