FLUX.2 Pro renders photoreal images up to 4 megapixels, takes up to eight reference images in one call, and hits exact pixel dimensions when a preset will not do. Three tiers, one parameter set, pay-as-you-go.
Required · put any text you want rendered in quotes
Public HTTPS URLs only (no base64) · up to 8 · each reference adds to the cost
1MP / 2MP (default) / 3MP / 4MP · higher tiers cost more
1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, 9:21
Try one of these prompts
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
One sample at the cheapest tier (1 image).
FLUX.2 Pro is the standard channel of Black Forest Labs' FLUX.2 image model on reAPI, with three tiers on one parameter surface: Pro for balanced quality and speed, Max for the highest detail, and Flex, which unlocks 1–50 sampling steps and guidance from 1.5 to 10. Generate from a prompt or from up to 8 reference images, at 1MP through 4MP across nine aspect ratios — or pass explicit width and height from 64 pixels per side up to a 4-megapixel budget. Billing is per image, set by tier and output resolution, plus a surcharge for each reference image you send.
Real-world workflows and production use cases you can build and ship with this model.
Send FLUX.2 Pro your product photo and describe the scene. Studio white, lived-in kitchen, autumn set dressing — the product keeps its shape, finish and label in every one. Eight references per call is what keeps it on-model across the set.
Open the playground
Give FLUX.2 Pro a width and height and you get that image, not the nearest preset plus a crop step. The pair overrides the resolution tier and the aspect ratio.
Switch the model id to the Flex tier and you get steps and guidance directly. Push guidance to hold the prompt tighter, push steps for more detail. That is the difference between one usable image from FLUX.2 Pro and a usable batch.
FLUX.2 Pro goes up to 4 megapixels, so hero images and print placements come out of the same call as your thumbnails. Pick the tier per request and the bill follows it.
Eight reference images per request. A FLUX.2 Pro scene can take its subject from one photo and its setting from another, and keep both recognisable.
FLUX.2 Pro, Max and Flex take identical requests. Benchmark them on your own prompts by swapping the model id — no rewrite.
Both generate and edit images from one API call. FLUX.2 Pro gives you explicit control — resolution tiers, exact dimensions, sampling parameters. Nano Banana optimises for a fast default path. Behaviour, not verdicts:
Comparison reflects publicly documented behavior at the time of writing. Vendors change capabilities and packaging frequently — verify against each vendor's current documentation before making a purchasing decision.
Sign up at reAPI and generate a key. Signup credits cover your first FLUX.2 Pro renders.
OpenPOST a prompt to the images endpoint with model set to flux-2-pro, flux-2-max or flux-2-flex-std. Add image_urls for references.
OpenThe FLUX.2 Pro request returns a task id. Poll until the status is completed, then read the image URL from the output.
Opencurl -X POST https://reapi.ai/api/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-2-pro",
"prompt": "a cinematic product photograph of an espresso machine",
"resolution": "2MP",
"size": "16:9"
}'Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.
401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.
Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.
A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.
Common questions about this model.
Explore more models in the same category.
Black Forest Labs
From $0.028 per image
Black Forest Labs
From $0.035 per image
Black Forest Labs
From $0.039 per image
From $0.028 per image
Try it in the playground or grab an API key to integrate now.