Black Forest Labs: FLUX.2 [pro]

FLUX.2 Pro covers image generation and iterative editing in the same model. Start from a written concept or an existing visual, then refine the scene and style for production illustrations, product scenes, or branded artwork.

Compare models

flux-2-pro

AvailableBlack Forest LabsImageSync / Async

Price: From $0.03
Released: Nov 25, 2025
Modalities: Image

About FLUX.2 [pro]

FLUX.2 [pro] is Black Forest Labs' production-grade FLUX.2 model for generating and editing images in one endpoint. It takes a text prompt and up to eight reference images, applies automatic prompt upsampling by default, and returns JPEG, PNG, or WebP. It is the general-purpose FLUX.2 choice between the speed-focused Klein models and the higher-fidelity FLUX.2 [max].

Where it works well

One model handles text-to-image and image editing, so a workflow can start from a prompt and refine with references.
It accepts up to eight reference images for composition and style guidance.
Automatic prompt upsampling can improve results from short prompts, and it can be disabled for literal control.

When to choose another model

It has no tunable guidance or step settings; FLUX.2 [flex] is the variant for typography-focused tuning.
For the most demanding consistency across edits, Black Forest Labs offers FLUX.2 [max] above it.
It is heavier than the Klein models, so low-latency previews are better served by those.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image editingText to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-image",
  "model": "flux-2-pro",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Pricing

per image

Verified price: —
Official price: How pricing works

	Official priceper image	Verified priceper image	Discount
Price	How pricing works	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 10, 2026, 02:23 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open FLUX.2 [pro] in Console with a prompt ready to edit or send.

Help me create an image with flux-2-pro using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Production illustrations
Create branded artwork from a brief, then adjust scene and style with follow-up edits using the same endpoint.
Product scene generation
Place a product reference into new settings and keep its appearance while changing background and lighting.
Edit-from-photo workflows
Start from a customer-supplied image and apply a written change, such as new colour or removed objects.

Prompt examples

Editorial illustration of a remote worker on a train, window view of mountains, muted autumn palette, textured paper look.

Using the attached headshot, put the person in a navy blazer against a plain grey backdrop; keep the face unchanged.

Three-quarter view of a minimalist desk lamp on a pale oak desk, soft morning light, product catalogue style.

FAQ

Can FLUX.2 [pro] edit existing images?

Yes. It handles text-to-image and image-to-image editing in the same model. Provide an instruction plus up to eight input images and it returns the edited or composed result.

What does prompt upsampling do on FLUX.2 [pro]?

It automatically rewrites your prompt to be more detailed before generating, which often helps short prompts. It is on by default; set disable_pup to turn it off if you need exact wording.

Should I use FLUX.2 [pro] or FLUX.2 [max]?

Start with [pro] for general production work. Move to [max] when you need the highest fidelity and the subject must stay consistent across many revisions, as in product and campaign imagery.

Does FLUX.2 [pro] support seeds?

Yes. An optional seed makes a request reproducible, so the same prompt, inputs, and seed can regenerate a similar result. It is useful for comparing prompt changes without randomness.

How much does FLUX.2 [pro] cost?

Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should FLUX.2 [pro] use?

Use https://api.tokenlab.sh/v1/images/generations for FLUX.2 [pro]. The request example below shows the matching code shape.

Which operations does FLUX.2 [pro] support?

FLUX.2 [pro] supports Image editing, Text to image. Select an operation above to see its endpoint and request example.