How do I refer to my reference images?

Write , or in the prompt, numbered in the order you upload. That is the notation Black Forest Labs documents for this model. In our tests "image 2" and "the second image" picked the right picture as well.

What is the difference between 1k and 2k?

1k is about one megapixel (1024 x 1024 or 1360 x 768) and 2k about four (for example 2720 x 1536). 2k takes longer and costs more; the aspect ratio and file format do not change the price.

Can I use my own LoRAs?

Not on this model page. Use FLUX 3 Klein LoRA, which runs the same distilled model with up to three LoRA files per request.

Per image, by size tier. In editing, each reference image after the first adds a small charge. Aspect ratio and output format do not change the price, and failed requests are not charged.

FLUX 3 Klein API — Uncensored NSFW Images, 1k and 2k

black-forest-labs/flux-3-klein/text-to-image

FLUX 3 Klein text to image draws one image from a written prompt on Black Forest Labs' step-distilled FLUX 3 Klein. Fifteen aspect ratios at 1k or 2k, JPEG, PNG or WebP, and no content filter.

From $0.012/image

Run model View API

Input

Text to image

Prompt414/5000

Aspect ratio

Resolutionaffects price

Output format

JPEGPNGWebP

Seed

Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run

Example result

Animate

Edit

Split into layers

{
  "model": "black-forest-labs/flux-3-klein/text-to-image",
  "input": {
    "aspect_ratio": "3:4",
    "resolution": "1k",
    "output_format": "jpeg",
    "seed": 101,
    "prompt": "Cinematic 35mm photograph in a Sicilian lemon grove at noon. An adult Italian woman about thirty with sun-streaked brown hair leans back against a weathered wooden picking ladder, a woven basket of lemons on her hip, wearing an ochre linen slip dress with one thin strap slipping off her shoulder. Dappled light through glossy leaves, warm skin, a slow sultry glance at the camera. Kodak Portra colour, soft grain."
  }
}

Introduction

FLUX 3 Klein Text to image draws one image from a written prompt on Black Forest Labs' FLUX 3 Klein, the 5.6B open-weights model released in October 2026, in its step-distilled build. Choose 1k or 2k and one of fifteen aspect ratios, get a JPEG, PNG or WebP back, and pay per image. The platform adds no content filter.

Choose a mode by starting material

What you have	Mode
a written description	FLUX 3 Klein Text to image
one to three images to change	FLUX 3 Klein Image editing

Key features & highlights

Photographic people in fifteen shapes

The model follows long captions closely and is at its best with people, skin, fabric and light. Fifteen aspect ratios from 3:1 to 1:3 cover banners, posts and phone screens, at about one megapixel (1k) or four (2k).

No content filter

Prompts, sources and results are not reviewed. In our tests unfiltered portraits of adult women rendered and unfiltered edits were carried out as asked; the strongest requests came back toned down by the model itself.

Request parameters

Request parameters for FLUX 3 Klein · Text to Image
Parameter	Required	Description
`prompt`	Yes	Required, up to 5,000 characters. Describe framing, subject, clothing, place, light and lens in full sentences; there is no negative prompt, so say what you want. at least 1 characters · at most 5000 characters
`aspect_ratio`	No	Fifteen shapes from 3:1 to 1:3; 1:1 by default. At 1k, 16:9 is 1360 x 768 and 3:4 is 880 x 1168. `1:1` · `16:9` · `9:16` · `4:3` · `3:4` · `3:2` · `2:3` · `4:5` · `5:4` · `21:9` · `9:21` · `2:1` · `1:2` · `3:1` · `1:3` · Default: `1:1`
`resolution`	No	1k (default) is about one megapixel; 2k is about four, for example 2720 x 1536 for a wide image. 2k costs more and takes longer. `1k` · `2k` · Default: `1k`
`output_format`	No	jpeg (default), png or webp. Same price for all three. `jpeg` · `png` · `webp` · Default: `jpeg`
`seed`	No	Optional, 0 to 2,147,483,647. In our tests the same seed and inputs gave the same image, so change one thing at a time. `≥ 0` · `≤ 2147483647`

Pricing

Billed per image by size tier (1k or 2k). Aspect ratio and file format do not change the price.

Pricing
Specification	Price
`1k`	$0.012 / image
`2k`	$0.048 / image

Use cases

Portraits and fashion stills

Sultry, clothed portraits in strong natural light, from lemon groves to whitewashed stairs, in the shape each placement needs.

Fast drafting

A few seconds per 1k image makes it practical to try many seeds and wordings, then rerun the keeper at 2k.

Explore key use-case tutorials

Prompt guide & pro tips

Write a full caption

Describe framing, subject, clothing, place, light and lens in full sentences. There is no negative prompt, so say what you want rather than what to avoid.

Draft at 1k, finish at 2k

Fix the seed while you work at 1k, then rerun the same inputs at 2k for the final image.

API quick start

# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $SPICY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
  -d '{
  "model": "black-forest-labs/flux-3-klein/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "resolution": "1k",
    "aspect_ratio": "1:1",
    "output_format": "jpeg"
  }
}'

# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $SPICY_API_KEY"

See the API reference for authentication, the complete schema, polling, and error handling.

Missing the model you need?

Tell us what to add and where you would use it. Requests go to the people who decide what gets onboarded next.

IMAGE API

FLUX 3 Klein API at a glance

Black Forest Labs' FLUX 3 Klein for text to image and multi-reference editing, at 1k or 2k, with no content filter.

Aspect ratios: 15; From 3:1 panoramas to 1:3 phone strips, every one at 1k or 2k.
Largest tier: ~4 MP; 2k is about four megapixels, for example 2720 x 1536 at 16:9; 1k is about one.
Edit references: 1 – 3; Name each source in the prompt as <ref_image_1>, <ref_image_2>, <ref_image_3>.
Typical 1k render: 2 – 5 s; Model time for most of our 1k text-to-image runs; edits and 2k take longer.
Output formats: 3; JPEG by default, or PNG or WebP at the same price.
Content filter: None; No review of prompts, source images or results.

Results

What you can make with FLUX 3 Klein

Two references
A dress from one photo, a woman from another
The prompt names <ref_image_1> and <ref_image_2>: the woman from the first photo now wears the cobalt halter dress from the second, with her face and freckles kept and the light moved to late-afternoon sun.
Edit with two references: a portrait and a dress on a hanger.
Text to image
Skin, linen and dappled noon light
One paragraph, 3:4 at 1k: a woman against a picking ladder in a lemon grove, light broken up by the leaves.
Text to image, 3:4 at 1k.
Single-image edit
Same man, new shirt, new hour
An overcast quay at morning became a low amber sunset; the sweater became an open linen shirt, and his face, beard and the net in his hands stayed.
Edit of one photo, auto shape.

More clips made with FLUX 3 Klein

Text to image, 4:5 at 1k.
Text to image, 16:9 at 1k.
Edit of one photo, auto shape.

Content test

Is FLUX 3 Klein uncensored? What we tested

We ran each level on our live setup and checked every clip frame by frame. A pass means the content was actually on screen, not just that the request went through.

Content levels tested on FLUX 3 Klein, by mode
Level	Image editing	Text to image
MildThe lightest prompts in the test	RendersTested Oct 16, 2026	RendersTested Oct 16, 2026
ModerateWhere filtered models start to refuse	RendersTested Oct 16, 2026	RendersTested Oct 16, 2026
StrongThe middle of the scale	RendersTested Oct 16, 2026	RendersTested Oct 16, 2026
Very strongWhere most models start to hold back	Not tested yet	Not tested yet
MaximumThe top of the scale	Not tested yet	Not tested yet

Renders: on screen as written. Softened: generated, but milder than what was written. Refused: rejected. Not tested yet: we have not run that level on that mode.

How each mode behaves

All modes: Two size tiers only, 1k and 2k; the 4K tier Black Forest Labs mentions is not offered here. No negative prompt, no step or guidance control and no bounding-box layout field. One image per request.
All modes: There is no content filter, but the model has limits of its own. In our tests unfiltered portraits of women came through with fine detail softened, while the strongest requests came back toned down.
Image editing: Editing takes one to three sources. With auto the result keeps the shape of the first image; pick a ratio to change it. Every source after the first adds a small charge.
All modes: Every person you describe or upload must be an adult. You are responsible for the lawfulness of what you generate and publish, including the rights of anyone shown in a source image. Generated media is retained for 14 days and then deleted.

Use cases

What to build with the FLUX 3 Klein API

Fashion and outfit swaps
Put a garment from one photo on a person from another, keep the face and change the light, in one request.
Sultry portraits and stills
Photographic people, skin and fabric, from moody lamplight to hard island sun, in fifteen shapes for every placement.
Fast drafting at scale
A few seconds per 1k image makes it practical to try many seeds and wordings before you commit to 2k.
Unfiltered imagery
Nothing is reviewed or filtered, and every unfiltered portrait and edit we tested came through.

Prompts

FLUX 3 Klein prompt examples you can copy

Paste one into the playground as it is, then change one thing at a time.

Image editing
Swap in a dress from another photo
Dress the woman from <ref_image_1> in the cobalt silk halter dress from <ref_image_2>. Keep her face, freckles and copper hair exactly. Move the light to a low golden late-afternoon sun; she leans back against the ochre wall, glancing over her bare shoulder with a slow, smouldering look while the sea breeze lifts her hair.
Why it works. Two uploads, named <ref_image_1> and <ref_image_2>. The garment comes from the second image, the person from the first, and the prompt lists what must stay.
This mode starts from your own image: add it in the playground before you run.
Try this prompt
Text to image
Lemon grove at noon
Cinematic 35mm photograph in a Sicilian lemon grove at noon. An adult Italian woman about thirty with sun-streaked brown hair leans back against a weathered wooden picking ladder, a woven basket of lemons on her hip, wearing an ochre linen slip dress with one thin strap slipping off her shoulder. Dappled light through glossy leaves, warm skin, a slow sultry glance at the camera. Kodak Portra colour, soft grain.
Why it works. A full caption in the order the model likes: place and light, person, clothing and the one detail that sets the mood, then lens and film stock.
Try this prompt
Text to image
Chapel steps at blue hour
Intimate photograph on the whitewashed steps of a small hilltop chapel at blue hour. An adult couple in their thirties, a Spanish woman in an off-the-shoulder cream cotton dress and a Lebanese man in a loose sand-coloured linen shirt, sit close with their foreheads touching, his hand resting on her bare shoulder, eyes nearly closed. A single warm lamp above the chapel door, indigo sky, soft film grain, 85mm lens, shallow depth of field.
Why it works. Two people, each with their own clothing and pose, and a single light source named; the model kept both faces distinct.
Try this prompt

Pricing

FLUX 3 Klein API pricing

One image starts at $0.012 at 1K and $0.048 at 2K.

The playground shows the exact price for your settings before you run. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.

See every price tier

Get started

How to use the FLUX 3 Klein API in three steps

Step 1
Write a full scene caption
Its makers say a full caption works best: framing, subject, clothing, place, light and lens in plain sentences. There is no negative prompt, so describe what you want to see.
Step 2
Name your sources when editing
Upload up to three images and refer to them as <ref_image_1>, <ref_image_2> and so on, in upload order. In our tests "image 2" and "the second image" also pointed at the right picture.
Step 3
Draft at 1k, finish at 2k
A 1k image takes a few seconds and costs a quarter of 2k. Fix the seed, settle the wording, then rerun the same seed at 2k.

Open the playground Get an API key

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

Why SpicyAPI

Why run FLUX 3 Klein on SpicyAPI

No filter from us
We add no content filter of our own. What the model renders is what you get back.
Tested, not guessed
Content labels come from real generations we ran and checked, with the test date on the page.
Pay per result, in dollars
No subscription and no credits. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.
One key for every model
One API key and balance cover image, video, audio and chat models, so you can explore more models from the same account.

FAQ

FLUX 3 Klein API FAQ

About FLUX 3 Klein

FLUX 3 Klein brings Black Forest Labs' newest open-weights image model to a plain API call: text to image and multi-reference editing at 1k or 2k, fifteen shapes, three file formats and no content filter.