Black Forest Labs FLUX.2 Pro: high-fidelity text-to-image with strong prompt adherence and crisp in-image text.
Provider: Black Forest Labs
Category: image generation
Endpoint: /v1/tasks
Status: Available
Cost: 74 Credits
Black Forest Labs' professional text-to-image model, available as an online image generator and through the asynchronous API for product imagery, posters, brand visuals, and detailed compositions.
From 75 Credits / image
$0.037 / image
Ready for generation
Configure your parameters and click "Run" to see the output here.
These images were generated with the current FLUX.2 Pro text-to-image endpoint across portrait, typography, complex composition, and cinematic scene prompts.
Choose an adjacent model by input type, quality tier, or generation speed.
FLUX.2 Pro is a text-to-image model from Black Forest Labs. HiAPI exposes it through the unified asynchronous task endpoint for workflows such as product imagery, posters, brand visuals, and compositions with detailed written constraints.
FLUX.2 Pro is priced by output resolution: 75 Credits per image at 0.5 MP, 100 at 1 MP, 150 at 2 MP, and 250 at 4 MP. Preset aspect ratios do not change the price within a resolution tier.
The current HiAPI endpoint supports 0.5 MP, 1 MP, 2 MP, and 4 MP tiers. With the custom aspect ratio, width and height can be set from 256 to 2048 and are rounded to multiples of 16; the resolution field is ignored in custom mode.
Text-to-Image
A speed- and cost-oriented FLUX option for drafts and batches.
FLUX.2 Pro is Black Forest Labs' professional text-to-image model. HiAPI currently exposes it as flux-2/text-to-image for marketing visuals, product and brand assets, posters with short written copy, portraits, and complex compositions that specify subjects, spatial relationships, camera language, and lighting.
The online image generator on this page and the API use the same model ID. Test a prompt, resolution, and output format in the Playground, then move the approved request into an asynchronous server workflow. This endpoint is text-to-image only and does not accept reference images; editing and multi-image composition belong to the separate FLUX.2 Image-to-Image model.
These specifications reflect the current public HiAPI request contract for FLUX.2 Pro Text-to-Image. The API documentation remains the source for full parameter definitions, callbacks, and task retrieval.
flux-2/text-to-imagePOST /v1/tasksIn custom mode, width and height may be set from 256 to 2048 and are rounded to multiples of 16; the resolution tier is ignored. The current endpoint exposes neither a negative prompt nor reference-image fields.
The online tool and API share the same model contract, so the workflow moves from prompt validation to production integration in three steps.
Define the subject, scene, composition, lighting, and short in-image copy, with the highest-priority constraints first.
Match resolution, aspect ratio, and WebP, JPG, or PNG output to the delivery surface.
Resolution
Output format
Aspect ratio
Validate the result in the Playground, then submit the same model ID asynchronously and retrieve it by callback or task query.
ResultAsync task
POST /v1/tasksModel
flux-2/text-to-imageThis is the minimum request needed to create an asynchronous FLUX.2 Pro task. Use the separate API documentation for full parameters, callbacks, and task retrieval.
POST /v1/tasksflux-2/text-to-imagecurl --request POST 'https://api.hiapi.ai/v1/tasks' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "flux-2/text-to-image",
"input": {
"prompt": "A minimalist product photo of a frosted glass perfume bottle on white marble, soft window light, generous negative space",
"aspect_ratio": "4:5",
"output_format": "webp",
"resolution": "1 MP"
}
}'taskId and an initial status; image generation continues asynchronously.Send model=flux-2/text-to-image and input.prompt to POST /v1/tasks. The asynchronous response returns a taskId. In production, configure callback.url for terminal notifications or query the task endpoint for the result. The separate API documentation contains the complete parameter and request reference.
Yes. Use the Playground on this page to test a prompt, aspect ratio, resolution, and output format, then use the same model ID when you are ready to integrate the API.
The flux-2/text-to-image endpoint on this page is for text-to-image generation. For reference-image editing or composition, use the separate flux-2/image-to-image model instead of adding image fields to this request.
Commercial use depends on the current Black Forest Labs terms, the HiAPI terms, and the content and jurisdiction involved. Review the latest licensing and compliance requirements before production use; this page is not legal or licensing advice.
FLUX.2 Pro is the high-fidelity production option with a published HiAPI model ID, parameter contract, and four resolution-based prices. FLUX.2 Klein is positioned for efficiency and faster iteration, but this repository does not currently contain a verifiable HiAPI Klein endpoint, price, or specification, so this page avoids publishing unsupported numbers or a dead link.