Black Forest Labs: FLUX.1 Kontext [max]
flux-kontext-max- Price
- From $0.08
- Context
- 4K
- Max output
- 4K
- Modalities
- Image
About FLUX.1 Kontext [max]
FLUX.1 Kontext [max] is the higher tier of Black Forest Labs' Kontext family, which edits or creates images from text plus reference images. It accepts up to four input images, with multi-image input marked experimental, and supports aspect ratios from 21:9 to 9:21. The maker now lists Kontext as a legacy line and recommends FLUX.2 for new editing work.
Where it works well
- Targeted edits follow a written instruction while the rest of the scene stays recognisable, because the model reads the input image as context.
- Black Forest Labs lists improved prompt adherence and typography in the [max] tier.
- Aspect ratios from 21:9 to 9:21 cover ultrawide banners and tall mobile layouts.
When to choose another model
- Black Forest Labs marks the Kontext models as legacy and recommends FLUX.2 [pro] or [flex] for new image editing.
- Multi-image input is described as experimental, so combining several references may be less predictable.
- Up to four input images, compared with eight on FLUX.2 [pro], [max], and [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 endpointPOST/v1/images/editscurl -X POST "https://api.tokenlab.sh/v1/images/edits" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "model": "flux-kontext-max", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
async | Not provided | Not provided | Not provided |
image | Not provided | Not provided | This public operation accepts source images. The maximum total source-image count is not yet verified. |
operation | Not provided | Not provided | Not provided |
prompt | Not provided | Not provided | Not provided |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
async | Not provided | Not provided | Not provided |
image | Not provided | Not provided | Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests. |
operation | Not provided | Not provided | Not provided |
prompt | Not provided | Not provided | Not provided |
Use `/v1/images/edits` for image-edit and `/v1/images/generations` for text-to-image.
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.
Image editing / Text to image
per request- Official price
- $0.08
- Verified price
- —
- Discount
- —
| Official priceper request | Verified priceper request | Discount | |
|---|---|---|---|
| Image editing / Text to image | $0.08 | — | — |
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
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open FLUX.1 Kontext [max] in Console with a prompt ready to edit or send.
Help me create an image with flux-kontext-max using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Iterative image editing
Make one change per step, such as swapping a background or adding an object, and keep the subject consistent.
Text replacement in images
Rewrite a sign, label, or poster headline in an existing picture using a plain instruction.
Character consistency
Place the same character in new scenes by supplying the earlier image as context.
Prompt examples
Change the shop sign to 'Open Late' in the same typeface and keep everything else as it is.
Put this character on a beach at sunset, same outfit, same illustration style.
Turn the daytime street into night with wet pavement and glowing windows, keep the people in place.
FAQ
How is Kontext [max] different from Kontext [pro]?
[max] is the higher tier, with Black Forest Labs citing improved prompt adherence and typography alongside consistent editing. [pro] covers the same text-plus-image workflow at a lighter tier. Both are now legacy lines.
Is FLUX.1 Kontext [max] still current?
Black Forest Labs labels it a legacy model and recommends FLUX.2 [pro] or [flex] for new editing tasks. It remains usable, which helps when you need to reproduce earlier results.
How many input images can Kontext [max] take?
Up to four, through input_image to input_image_4, as base64 data or URLs. The multi-reference feature is marked experimental in the documentation, so test it on your own material.
Can Kontext [max] create images from scratch?
Yes. It both edits and creates: with no input image it behaves as a text-to-image model, and with images it edits using them as context.
How much does FLUX.1 Kontext [max] cost?
On TokenLab, FLUX.1 Kontext [max] costs $0.08 per request. The pricing table above shows the full breakdown. 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.1 Kontext [max] use?
Use https://api.tokenlab.sh/v1/images/edits for FLUX.1 Kontext [max]. The request example below shows the matching code shape.
Which operations does FLUX.1 Kontext [max] support?
FLUX.1 Kontext [max] supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare FLUX.1 Kontext [max]
Guides that use FLUX.1 Kontext [max]
Sources
Reviewed Oct 2, 2026
More from Black Forest Labs