Black Forest Labs: FLUX.2 [max]

FLUX.2 Max emphasizes detailed, realistic imagery and precise edits. It is suited to product visuals and campaign artwork where maintaining a subject's appearance across revisions matters as much as the initial composition.

Compare models

flux-2-max

AvailableBlack Forest LabsImageSync / Async

Price: From $0.07
Modalities: Image

About FLUX.2 [max]

FLUX.2 [max] is the highest-fidelity hosted model in Black Forest Labs' FLUX.2 line, built for strong prompt adherence and consistent edits. It generates from a prompt and edits with as many as eight input images. Compared with FLUX.2 [pro] it is aimed at work where a subject must look the same across revisions, such as product visuals and campaign art.

Where it works well

Black Forest Labs lists strong prompt adherence and editing consistency as its purpose, which suits revision-heavy workflows.
Up to eight reference images let one request combine product shots, style references, and backgrounds.
Automatic prompt upsampling is on by default and can be switched off when you need exact wording followed.

When to choose another model

It is the top FLUX.2 tier, so it is slower than the Klein models for drafts and previews.
No guidance or step controls are exposed, unlike FLUX.2 [flex], so typography tuning is limited.
Black Forest Labs documents no search or grounding feature for it, so it will not look up current facts for a prompt.

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-max",
  "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, 06:53 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 [max] in Console with a prompt ready to edit or send.

Help me create an image with flux-2-max 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

Product campaign artwork
Keep a product's shape, colour, and logo stable while changing the scene, season, or camera angle across a set of images.
Realistic marketing imagery
Generate detailed photographic scenes for ads and landing pages, then edit them with precise follow-up instructions.
Multi-image brand composites
Merge model, product, and environment references into one coherent frame for a catalogue shot.

Prompt examples

Use the three attached images: place this sofa from image 1 in the living room of image 2, with the lighting of image 3.

Photorealistic running shoe on a wet city street at night, reflections of shop signs, 85mm lens look.

Same bottle as the reference, now on a marble counter with morning light and a sprig of rosemary beside it.

FAQ

What is FLUX.2 [max] best for?

Work that needs fidelity and consistency: product visuals, campaign artwork, and edits where the subject must remain recognisable. Black Forest Labs describes it as combining strong prompt adherence with editing consistency.

How does FLUX.2 [max] differ from FLUX.2 [pro]?

Both take text and up to eight reference images. [max] is the higher-quality tier aimed at consistent, detailed results, while [pro] covers general generation and editing at a lighter tier. Try [pro] first and move to [max] if consistency falls short.

Can I turn off prompt upsampling on FLUX.2 [max]?

Yes. Upsampling rewrites the prompt for better adherence and is on by default; the disable_pup option switches it off, which helps when you need your wording followed literally.

What output formats does FLUX.2 [max] return?

JPEG by default, with PNG and WebP also available. Width and height can be set from a 64 pixel minimum, or left at their defaults for the model to pick suitable dimensions.

How much does FLUX.2 [max] 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 [max] use?

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

Which operations does FLUX.2 [max] support?

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