Black Forest Labs: FLUX.2 [klein] 4B

FLUX.2 Klein 4B is the compact, speed-focused member of the Klein image family. It supports creating images and revising an existing picture, making it useful for interactive design experiments and quick concept iteration.

Compare models

flux-2-klein-4b

AvailableBlack Forest LabsImageSync / Async

Price: From $0.014
Modalities: Image

About FLUX.2 [klein] 4B

FLUX.2 [klein] 4B is the smallest and fastest model in Black Forest Labs' FLUX.2 line, released with open weights that run on consumer GPUs. It handles text-to-image generation and image editing with up to four reference images. It gives up some quality against the larger FLUX.2 models in return for speed, which suits interactive tools and rapid iteration.

Where it works well

Black Forest Labs calls it the fastest, most lightweight FLUX.2 model, so it fits tools where a user waits for each image.
Open weights that run on consumer GPUs mean the same model can be prototyped locally before you call it in production.
It accepts up to four reference images, so edits and guided generation do not need a bigger model.

When to choose another model

Black Forest Labs notes it trades some quality for speed; use the 9B Klein or FLUX.2 [pro] when image fidelity is the priority.
Four reference images is half the eight allowed by FLUX.2 [pro], [max], and [flex], which limits complex multi-source composition.
It has no guidance or step controls like FLUX.2 [flex], so typography-critical layouts are better placed on [flex].

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-4b",
  "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, 02:20 AM 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] 4B in Console with a prompt ready to edit or send.

Help me create an image with flux-2-klein-4b 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

Live design previews
Show a generated or edited image within a second or two of each change a user makes in a design tool.
Batch thumbnail drafts
Produce many cheap first-pass images for a catalogue, then re-render selected ones on a higher tier.
Local-to-hosted prototyping
Develop against the open-weight 4B model on a workstation, then call the same model through the API at volume.

Prompt examples

A low-poly red fox sitting in a snowy forest, soft blue shadows, centered composition.

Take the attached sneaker photo and recolour the sole to mint green, keep everything else unchanged.

Flat icon set: coffee cup, laptop, notebook, plant, all in the same rounded outline style.

FAQ

What is FLUX.2 [klein] 4B?

It is the compact member of Black Forest Labs' Klein family within FLUX.2, with four billion parameters. It generates and edits images, ships open weights for consumer GPUs, and is positioned as the fastest option in the FLUX.2 lineup.

How does the 4B differ from FLUX.2 [klein] 9B?

The 4B is the faster and lighter of the two, while the 9B is larger and balances quality and speed. Both accept up to four reference images; pick the 4B for latency and the 9B for better image quality.

Can FLUX.2 [klein] 4B edit photos?

Yes. Send the instruction plus up to four input images and it returns an edited or newly composed image. It is built for quick edits rather than the most demanding retouching jobs.

When should I choose something larger than the 4B?

Move up when you need finer detail, more reference images, or reliable lettering. FLUX.2 [pro] and [max] take eight references, and [flex] adds typography focus and tunable guidance.

How much does FLUX.2 [klein] 4B 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] 4B use?

Use https://api.tokenlab.sh/v1/images/generations for FLUX.2 [klein] 4B. The request example below shows the matching code shape.

Which operations does FLUX.2 [klein] 4B support?

FLUX.2 [klein] 4B supports Image editing, Text to image. Select an operation above to see its endpoint and request example.