FLUX vs modl
FLUX
bfl.ai
modl
modl.runSide by side
| Figure | FLUX | modl |
|---|---|---|
| Price from | $0.01/mo | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | Yes | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| macOS | Yes | Yes |
| Linux | Yes | Yes |
| API | Yes | — |
| Self-hosted | Yes | — |
| Plans published | 22 | 0 |
| Spec score · AI image generators | 9.4 (#3) | 7.7 (#73) |
| Free plan | Yes | Yes |
| Image editing | FLUX.2 models support prompt-driven image editing, with editing prices listed separately from text-to-image prices. | Yes |
| Image generation | FLUX.2 models generate images from text prompts and support megapixel-based output pricing. | The CLI generates images from text prompts and edits existing images with natural-language instructions. |
Plans
FLUX
- FLUX.2 [max]$0.07 a month
- FLUX.2 [pro]$0.03 a month
- FLUX.2 [klein] 9B$0.02 a month
- FLUX.2 [klein] 4B$0.01 a month
- FLUX.2 [flex]$0.05 a month
- Open weights — FLUX.2 [dev]Free
- Open weights — FLUX.2 [klein] 4BFree
- FLUX.2 [klein] 4B$0.01, paid once
- Pay as you go — FLUX.2 [klein] 4B$0.01, paid once
- FLUX.2 [klein] 9B$0.02, paid once
In their own words
FLUX
FLUX is a set of AI models from Black Forest Labs for creating and editing images and video. FLUX 3 can make video with synchronized audio from text or images, or continue a clip, with a maximum length of 20 seconds. FLUX.2 generates and edits images up to 4 MP, with multi-reference editing, hex color control and text rendering. FLUX Tools add outpainting, object erasing, virtual try-on, video upscaling and deblurring. Access options include a browser playground, API and downloadable weights for self-hosting. Platforms listed are API, Linux, macOS, self-hosted, web and Windows. There is a free plan; the listed pay-as-you-go FLUX.2 [klein] 4B option is $0.01, paid once, with additional megapixel and reference-image charges. API use includes full commercial rights without a separate license; rights for open-weight models depend on their license. Submitted prompts, uploads, tasks and outputs may be used to train and improve models, with an email opt-out route.