Black Forest Labs: FLUX.2 [klein] 9B

FLUX.2 Klein 9B is the larger Klein variant for prompt-based image creation and editing. It offers another option within the fast Klein family when evaluating how a model handles subjects, composition, and written instructions.

Compare models

flux-2-klein-9b

AvailableBlack Forest LabsImageSync / Async

Price: From $0.015
Modalities: Image

About FLUX.2 [klein] 9B

FLUX.2 [klein] 9B is the larger of the two Klein models in Black Forest Labs' FLUX.2 line, with nine billion parameters and open weights. It generates images from text and edits them from up to four reference images with sub-second inference, according to the maker. It balances quality and speed, sitting between the 4B Klein and FLUX.2 [pro].

Where it works well

Black Forest Labs advertises sub-second inference with open weights, which makes it practical for interactive generation.
Positioned to balance quality and speed, it gives more detail than the 4B Klein at modest extra latency.
Up to four reference images support editing and guided generation in a single request.

When to choose another model

It is smaller than FLUX.2 [pro] and [max], so complex scenes and precise edits may need those models.
Reference images are capped at four, against eight on the pro, max, and flex tiers.
It lacks the tunable guidance and step settings of FLUX.2 [flex] for fine control over typography.

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-klein-9b",
  "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 11, 2026, 05:59 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 [klein] 9B in Console with a prompt ready to edit or send.

Help me create an image with flux-2-klein-9b 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

Interactive image tools
Back an in-app generator or editor where users expect a result almost immediately after typing a prompt.
Product variation drafts
Feed one product photo and ask for colour, background, or setting changes to review options quickly.
Style exploration
Try several art directions from the same prompt before sending the chosen one to a higher-quality model.

Prompt examples

Editorial illustration of a lighthouse in a storm, ink and gouache look, limited palette of teal and ochre.

Using the attached portrait, change the background to a sunlit library and keep the face and clothing identical.

Product shot of a matte black water bottle on wet slate, rim lighting, plenty of empty space at right.

FAQ

Is FLUX.2 [klein] 9B open-weight?

Yes. The weights are open, but under the FLUX Non-Commercial License, which does not allow commercial use of the self-hosted model. The 4B Klein models are Apache 2.0 if you need a commercial self-hosted option.

How is the 9B different from the 4B Klein?

The 9B has more parameters and is described as balancing quality and speed; the 4B is the fastest, most lightweight option. Both take up to four reference images and accept the same request options.

Does FLUX.2 [klein] 9B support image editing?

Yes. Pass up to four reference images with an instruction and it edits or recombines them. It handles quick edits well; very precise retouching is better placed on FLUX.2 [pro] or [max].

Which should I use, the 9B Klein or FLUX.2 [pro]?

Use the 9B Klein when speed and volume matter, such as previews and drafts. Use FLUX.2 [pro] when you want higher fidelity and up to eight references for final production images.

How much does FLUX.2 [klein] 9B 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 [klein] 9B use?

Use https://api.tokenlab.sh/v1/images/generations for FLUX.2 [klein] 9B. The request example below shows the matching code shape.

Which operations does FLUX.2 [klein] 9B support?

FLUX.2 [klein] 9B supports Image editing, Text to image. Select an operation above to see its endpoint and request example.