Skip to main content

FLUX.2 Pro

FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 family, released on 25 November 2025. BFL, the Freiburg lab founded by the researchers behind Stable Diffusion, positions it as the model you call when you want studio-grade photorealism without tuning anything: no steps, no guidance, one call. It is priced by the megapixel, which makes a 1K image about three cents.

Anvisha PaiAnvisha Pai, Co-founder & CEO, ModaTested

Black Forest Labs · released

FLUX.2 Pro self-portrait, hyperreal studio photograph
FLUX.2 Pro drawing itself as hyperreal studio photograph, generated by us.
What we asked for

A self-portrait of FLUX.2 Pro, Black Forest Labs' image model, as a hyperreal studio photograph: a sculpted figure made of flowing black glass on a plinth, a single word 'FLUX' etched into the base, dramatic rim light, macro detail in the reflections, dark studio backdrop.

fal-ai/flux-2-pro
image_size: {"width":1360,"height":1024}, output_format: png, num_images: 1
returned 1360 by 1024 pixels

At a glance

Price
$0.03 for the first megapixel and $0.015 for each extra, so a 1K image is three cents and a 1920 by 1080 one about four and a half.
Any size
Exact width and height, priced by area.
No tuning
No steps or guidance; that is what [flex] is for.
Photorealism
BFL's pitch and the FLUX reputation; the face, food and product samples below are the test.
Open siblings
FLUX.2 [dev] and [klein] are downloadable if you would rather run it yourself.

Other FLUX models: FLUX.2 Flex, FLUX.2 Max. Compare all 3.

Anvisha's take

FLUX.2 Pro is the photographer of this batch. The portrait is the most convincing on the site, the hard composition was exact down to three ice cubes, and it did all twelve in 8 to 16 seconds for three to four and a half cents each. It is weaker on layout: the poster is correct but oddly composed, and the infographic, while clean, is plain. The edit redrew the dripper. My rule is Pro for anything that should look like a photo and something else for anything that should look designed.

FLUX.2 Pro real output: the same 12 prompts every model gets

Every model on this site gets the same 12 prompts, so you can compare like with like. These are the pictures FLUX.2 Pro returned, one try each, nothing re-rolled or retouched. Generated on . The 12 pictures took 8 to 16 seconds each and cost $0.495 in total.

FLUX.2 Pro output for the text in an image prompt
Text in an image10s · $0.045

Spelling, kerning and hierarchy of three lines of set text.

What we asked for

A concert poster that reads 'MODA SUMMER SESSIONS' in large bold type, with the subtitle 'Friday 12 June, 8pm, Roundhouse' and a smaller line 'Tickets at the door'. Risograph style, two colours, tangerine and navy, grainy ink texture.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1360}, output_format: png, num_images: 1
returned 1024 by 1360 pixels

FLUX.2 Pro output for the product on white prompt
Product on white8s · $0.03

Catalogue lighting, a clean seamless background and a believable contact shadow.

What we asked for

Studio product photograph of a matte black ceramic pour-over coffee dripper on a seamless white background, soft top light, subtle contact shadow, centred, catalogue style.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1024}, output_format: png, num_images: 1
returned 1024 by 1024 pixels

FLUX.2 Pro output for the face and hands prompt
Face and hands13s · $0.045

A natural face, correct finger count and hands holding an object.

What we asked for

Close-up portrait of a woman in her 40s with short grey hair, laughing, holding a red ceramic mug with both hands, natural window light, 85mm lens, shallow depth of field.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1360}, output_format: png, num_images: 1
returned 1024 by 1360 pixels

FLUX.2 Pro output for the logo mark prompt
Logo mark8s · $0.03

A flat single-colour mark with a legible wordmark and no gradients or photo texture.

What we asked for

A flat vector logo mark for a bicycle repair shop called 'Spoke & Chain': a single-colour icon combining a chain link and a wheel spoke, with the wordmark below in a geometric sans-serif, black on white.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1024}, output_format: png, num_images: 1
returned 1024 by 1024 pixels

FLUX.2 Pro output for the busy scene prompt
Busy scene10s · $0.045

Many distinct objects and people in one frame without merging or duplicating them.

What we asked for

A crowded Saturday farmers market seen from slightly above: at least twelve stalls with striped awnings, shoppers carrying tote bags, a dog on a leash, crates of oranges, a musician with a guitar, bunting overhead, late morning light.

fal-ai/flux-2-pro
image_size: {"width":1360,"height":1024}, output_format: png, num_images: 1
returned 1360 by 1024 pixels

FLUX.2 Pro output for the specific art style prompt
Specific art style12s · $0.045

A named historical style applied faithfully rather than a generic painterly look.

What we asked for

A lighthouse on a rocky cliff during a storm, in the style of a Japanese ukiyo-e woodblock print, with visible wood grain texture, flat colour areas and a bokashi gradient sky.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1360}, output_format: png, num_images: 1
returned 1024 by 1360 pixels

FLUX.2 Pro output for the chart prompt
Chart14s · $0.045

Six labelled bars at the stated heights, in order, with readable axes.

What we asked for

A clean bar chart titled 'Monthly active users' showing six months, January through June, with the values 120, 150, 180, 170, 220 and 260, labelled axes, white background, one accent colour, no 3D effects.

fal-ai/flux-2-pro
image_size: {"width":1360,"height":1024}, output_format: png, num_images: 1
returned 1360 by 1024 pixels

FLUX.2 Pro output for the wide aspect ratio prompt
Wide aspect ratio13s · $0.045

A 21:9 composition that leaves the left third clear for headline text.

What we asked for

Website hero banner: a wide panorama of a sunlit modern co-working space with plants, the left third of the frame kept as clear wall space for text, warm neutral palette.

fal-ai/flux-2-pro
image_size: {"width":2016,"height":864}, output_format: png, num_images: 1
returned 2016 by 864 pixels

FLUX.2 Pro output for the infographic with steps prompt
Infographic with steps15s · $0.045

Four numbered steps in the given order with their exact wording, plus an icon each.

What we asked for

An infographic card titled 'How to brew pour-over' with four numbered steps in this order: 1. Rinse the filter, 2. Bloom for 30 seconds, 3. Pour in slow circles, 4. Wait 3 minutes. A simple icon beside each step, muted palette, clean sans-serif type.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1360}, output_format: png, num_images: 1
returned 1024 by 1360 pixels

FLUX.2 Pro output for the food photography prompt
Food photography10s · $0.03

Appetising, menu-grade food with correct textures and no melted anatomy.

What we asked for

Overhead photograph of a margherita pizza on a wooden board, fresh basil leaves, one slice pulled out with the cheese stretching, restaurant menu photography, natural light.

fal-ai/flux-2-pro
image_size: {"width":1024,"height":1024}, output_format: png, num_images: 1
returned 1024 by 1024 pixels

FLUX.2 Pro output for the hard composition prompt
Hard composition13s · $0.045

Exact counts and left-right placement of five named objects.

What we asked for

A glass of water on a wooden table with exactly three ice cubes in it, a yellow pencil resting across the rim of the glass, a blue book to the left of the glass and a red apple to the right, photographed from table height.

fal-ai/flux-2-pro
image_size: {"width":1360,"height":1024}, output_format: png, num_images: 1
returned 1360 by 1024 pixels

FLUX.2 Pro output for the edit an existing image prompt
Edit an existing image16s · $0.045

Change one object's colour and add a part while leaving background, light and framing untouched.

What we asked for

Change the coffee dripper to a deep forest green and add a small brass handle on its right side. Keep the background, lighting and composition exactly as they are. (applied to the product on white result above)

fal-ai/flux-2-pro/edit
image_size: {"width":1024,"height":1024}, output_format: png, num_images: 1
returned 1024 by 1024 pixels

How the cost under each picture was worked out: fal's FLUX.2 [pro] rate of $0.03 for the first output megapixel plus $0.015 per extra megapixel, rounded up to the nearest 1024x1024 megapixel as fal states: 1 for the 1024x1024 output; fal does not return the charge.

FLUX.2 Pro pricing

WhereUnitPriceSource
BFL API1K image
BFL lists [pro] from $0.03 for text-to-image and from $0.045 for editing, by the megapixel.
$0.03BFL pricing, read
fal1024 by 1024 image
$0.03 for the first megapixel of output plus $0.015 per extra megapixel of input and output. fal's own examples: 1920 by 1080 is $0.045.
$0.03fal model page, read

Is FLUX.2 Pro free?

Black Forest Labs sells FLUX.2 by the megapixel through its own API and partners and does not run a free consumer app. Free access exists only through third parties: hosts and creative apps that bundle FLUX with sign-up credits, and the open-weight FLUX.2 [dev] and [klein] models you can run yourself.

  • BFL API: pay per megapixel, no free tier. Batches multiply the base price by the image count.
  • Open weights: FLUX.2 [dev] and [klein] can be downloaded and run locally under their licences; [klein] is Apache 2.0.
  • Third-party apps: sites like Krea, Freepik and Mistral's Le Chat bundle FLUX models with their own free allowances.

BFL pricing, read

Where to use FLUX.2 Pro

  • BFL API · Black Forest Labs' own endpoint, flux-2-pro.
  • fal · Per-megapixel pricing, generate and edit endpoints, custom sizes.
  • Replicate · Hosted under black-forest-labs.
  • Moda · Available inside the Moda design agent.

Generate with FLUX.2 Pro in Moda

Pick FLUX.2 Pro in the Moda design agent, then edit the result as vectors, text and layers rather than a flat image.

Open Moda →

What we noticed running FLUX.2 Pro

  • The most photographic portrait on the site: skin, knit, hands and window light all read as a real camera. See the face and hands picture.
  • Counts and placement exact: three ice cubes, pencil across the rim, book left, apple right. See the hard composition picture.
  • Four headings, exact wording, nothing invented, but plain: grey boxes, a mismatched icon or two, no hierarchy. Correct rather than designed. See the infographic with steps picture.
  • All three lines correct and a strong risograph texture, on a composition that leaves a torn block of navy filling half the sheet. Text renders; layout is not its instinct. See the text in an image picture.
  • Edits are re-draws. Green and brass arrived on a smaller, smoother cup with no base. See the edit an existing image picture.
  • Fast and even: 8 to 16 seconds per picture, median 13.
  • Custom sizes are honoured to the pixel: 1024 by 1360, 1360 by 1024 and 2016 by 864 came back as requested. fal rounds each up to whole 1024 by 1024 megapixels, so all three billed as two, $0.045, and only the square 1K image billed as one.

FLUX.2 Pro limits and API parameters

LimitValue
Output sizeAny width and height, priced by the megapixel; our 21:9 run at 2016 by 864 came back at that exact size.
fal API reference, read
Transparent backgroundNot supported on the hosted endpoints.
fal API reference, read
Reference imagesMultiple, through the edit endpoint; BFL cites up to 10 for [flex].
FLUX.2 announcement, read
Every setting, for developers

fal (fal-ai/flux-2-pro)

fal API reference, read

ParameterTypeValuesDefault
promptstringAny text
Required.
image_sizeenum or objectsquare_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width, height}landscape_4_3
seedintegerAny integer
safety_toleranceenum1 to 5, 1 strictest2
enable_safety_checkerbooleantrue, false
Turning it off needs account authorisation.
true
output_formatenumjpeg, pngjpeg
image_urlslist of URLsReference images
Edit endpoint only, where it is required.

What FLUX.2 Pro will not draw

Black Forest Labs licenses the FLUX.2 API models for commercial use and ships them with a safety checker that hosts leave on by default; fal exposes a safety_tolerance dial from 1 to 5, 1 strictest, and turning the checker off entirely needs account authorisation. The usual prohibitions apply: sexual content involving minors, non-consensual intimate imagery, and deceptive depictions of real people. There is no adult mode on the hosted models.

fal API reference, read

Alternatives to FLUX.2 Pro

Frequently asked questions

What is FLUX.2 Pro?

FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 image family, released on 25 November 2025 and sold by the megapixel through BFL's API, fal and Replicate.

Is FLUX AI free?

Not from Black Forest Labs, which sells its API by the megapixel. The open-weight FLUX.2 [dev] and [klein] models can be run locally, and several creative apps bundle FLUX with their own free credits.

How much does FLUX.2 Pro cost?

About $0.03 for a 1K image: $0.03 for the first megapixel plus $0.015 per extra megapixel on fal, and from $0.03 on BFL's own API, read on 9 September 2026.

Who owns FLUX AI?

Black Forest Labs, a company founded in 2024 in Freiburg, Germany, by former Stability AI researchers who helped create Stable Diffusion. The many flux-branded websites on page one of a search are unrelated resellers.

How this page is made

Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.

Anvisha Pai

Anvisha Pai

Co-founder & CEO, Moda

Anvisha is the CEO of Moda and a repeat, Y Combinator-backed startup founder. She was previously a PM at Dropbox. She believes nobody should need a design degree to make something that looks great.