GLM-5.2 is live — Z.AI's flagship with a 1M-token lossless contextfrom $0.900 per 1M tokens

FLUX Kontext — Prompt-Only Image Editing and Generation

FLUX Kontext edits a real photo from one plain sentence — no masks, no layers, no selection tools. The same FLUX Kontext endpoint also generates images from scratch, so a single integration covers both jobs. Choose the pro tier for fast production work, or the max tier when typography and prompt adherence have to be exact.

Input

Required · to replace words in an image, write: Replace 'old text' with 'new text'

Public HTTPS URLs only (no base64) · up to 4 images · leave empty for text-to-image

1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, 9:21 · does not change the price

png (default), jpeg or webp

Estimated cost36 credits≈ $0.036
Result

Try one of these prompts

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

FLUX Kontext product photo edited into several background variants

Product photo variants without a studio reshoot

Point FLUX Kontext at one product shot and describe the variant you need — new backdrop, seasonal setting, different colourway. It edits in place instead of regenerating the scene, so the product keeps its shape and label while everything around it changes.

Open the playground
FLUX Kontext replacing text on a shop sign while keeping the original lettering style

Localising signage and on-image copy

Write Replace 'SALE' with 'REBAJAS' and the sign keeps its typeface, paint texture and perspective. For teams shipping one creative into several markets, FLUX Kontext removes the round trip back to a designer.

FLUX Kontext keeping one character consistent across several edited scenes

Keeping one character consistent across a series

Start from a single reference portrait and let FLUX Kontext carry that person through new scenes, outfits and weather. Identity holds across a chain of edits, which is what makes FLUX Kontext usable for storyboards, explainer sequences and character-led ad sets rather than one-off images.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

CategoryUnitPrice
Pro
Per image1 image
$0.036
36 credits
Max
Per image1 image
$0.071
71 credits

Why reAPI

Edits from a sentence, not a mask

No selection tool. No layer stack. No inpainting mask. You describe the change and FLUX Kontext applies it to the region that matters — an entire editing pipeline collapsed into one call.

Characters that survive iteration

Black Forest Labs builds FLUX Kontext around context awareness, and it shows most when you edit the same subject repeatedly. A face stays recognisable through a sequence of changes instead of drifting into a different person by the third pass.

Fast enough for interactive tools

The pro tier runs at roughly five to six seconds per image. Quick enough to put FLUX Kontext behind a user-facing editor, where people tweak a prompt and expect to see the result — not queue a job and come back later.

FLUX Kontext vs Adobe Firefly

Both edit and generate images with commercial use in mind, but they are built for different operators. FLUX Kontext is an API you call from your own product; Firefly is a creative-suite tool a designer drives by hand. The rows below compare how each one behaves rather than which is better.

Capability
FLUX Kontext on reAPI
Adobe Firefly
How you pay
Pay-as-you-go per generated image, no subscription and no seat cost.
Bundled into Creative Cloud plans or sold as generative credit allowances.
Editing method
Describe the change in a sentence; no mask, selection or layer work needed.
Generative fill driven by a brush or selection inside the editor.
Character consistency
FLUX Kontext is built around holding a subject's identity across a chain of iterative edits.
Consistency depends on reference features and manual retouching between steps.
In-image text replacement
Explicit Replace 'x' with 'y' grammar that preserves the original lettering.
Text is typically handled with real type layers in the design tool.
Output resolution
Fixed at roughly one megapixel for every aspect ratio — upscale separately if you need more.
Higher native output sizes and an upscaling workflow built into the suite.
How it fits your stack
REST call plus task polling, so it drops into a backend or a user-facing editor.
Desktop and web applications aimed at hands-on creative work.

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.

Integrate FLUX Kontext in three steps

  1. step 01

    Create an API key

    Sign up at reAPI and generate an API key from your dashboard. Signup credits let you try FLUX Kontext before you add any funds.

    Open
  2. step 02

    Send your first request

    POST a prompt to the images endpoint with model set to flux-kontext-pro or flux-kontext-max. Add image_urls when you want an edit instead of a fresh generation.

    Open
  3. step 03

    Poll for the result

    The FLUX Kontext request returns a task id. Poll the tasks endpoint until the status is completed, then read the image URL from the output. Full request and response shapes are in the API docs.

    Open

Frequently asked questions

Common questions about this model.

FLUX Kontext is an image model from Black Forest Labs that combines text-to-image generation with context-aware editing in a single endpoint. You either send a prompt on its own to generate an image, or send a prompt plus reference images to edit them. On reAPI, FLUX Kontext is available in two tiers, flux-kontext-pro and flux-kontext-max.

Related models

Explore more models in the same category.

View all models
start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.

Try FLUX KontextView API Docs