# FLUX.2 [klein] 9B

> Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support

## Quick Reference

- Model ID: flux.2-klein-9b
- Creator: Black Forest Labs
- Status: active
- Family: flux.2
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 2048x2048
- Max Input Images: 4
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/flux.2-klein-9b?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Edit instruction for the image. Modes: Image Edit, Text to Image
- `seed` (integer): Random seed for reproducibility. Modes: Image Edit, Text to Image

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: auto, 1563x670, 670x1564, 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1145x916, 916x1145, 1183x887. Modes: Image Edit, Text to Image
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: auto, 9:21, 9:16, 2:3, 3:4, 4:5, 1:1, 5:4, 4:3, 3:2, 16:9, 21:9. Modes: Image Edit, Text to Image
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: auto, 1K. Modes: Image Edit, Text to Image

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Image Edit, Text to Image
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Image Edit, Text to Image
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF). Modes: Image Edit, Text to Image
- `n` (integer): Number of images to generate. Default: 1. Modes: Image Edit, Text to Image

### Additional Parameters

- `disable_safety_checker` (boolean): Disable safety checker for generated images.. Modes: Text to Image, Image Edit. Only available via replicate
- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Modes: Image Edit, Text to Image. Only available via fal
- `go_fast` (boolean): Run faster predictions with additional optimizations.. Modes: Text to Image, Image Edit. Only available via replicate
- `megapixels` (string): Resolution in megapixels. Values: 0.25, 0.5, 1, 2, 4. Modes: Text to Image, Image Edit. Only available via replicate
- `num_inference_steps` (integer): The number of inference steps to perform.. Modes: Image Edit, Text to Image. Only available via fal
- `output_quality` (integer): Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.. Modes: Text to Image, Image Edit. Only available via replicate
- `sync_mode` (boolean): If `True`, the media will be returned as a data URI. Output is not stored when this is True.. Modes: Image Edit, Text to Image. Only available via fal


## Model Identifiers

- Primary Slug: flux.2-klein-9b
- Aliases: flux-2-klein-9b

## Dates

- Released: January 2026

## Tags

image-generation, text-to-image, image-editing, open-weights

## Available Providers

### fal.ai

- Config Key: fal/flux.2-klein-9b-edit
- Provider Model ID: fal-ai/flux-2/klein/9b/edit
- Pricing: $0.011/megapixel, $0.011/megapixel
  - Source: https://fal.ai/models/fal-ai/flux-2/klein/9b/edit

### Replicate

- Config Key: replicate/flux.2-klein-9b
- Provider Model ID: black-forest-labs/flux-2-klein-9b
- Pricing: $0.0020/megapixel, $0.015/megapixel
  - Source: https://replicate.com/black-forest-labs/flux-2-klein-9b

### fal.ai

- Config Key: fal/flux.2-klein-9b
- Provider Model ID: fal-ai/flux-2/klein/9b
- Pricing: $0.0060/megapixel
  - Source: https://fal.ai/models/fal-ai/flux-2/klein/9b


## Performance Metrics

Provider performance over the last 30 days.

### fal

- Median Generation Time (p50): 3389ms
- 95th Percentile Generation Time (p95): 6788ms
- Average Generation Time: 3939ms
- Success Rate: 100.0%
- Total Requests: 10
- Time to First Byte (p50): 1999ms
- Time to First Byte (p95): 6497ms


## Arena Benchmarks

### Geometric Composition

- Elo: 1270
- Record: 11W / 4L / 1T (16 battles)
- Rank: #4 of 70

### Magic Burger Explosion: Fiery Photorealism Challenge

- Elo: 1226
- Record: 16W / 15L / 2T (33 battles)
- Rank: #6 of 69

### The Halloween Invitation

- Elo: 1214
- Record: 10W / 1L / 0T (11 battles)
- Rank: #5 of 70

### Candid Street Photography

- Elo: 1211
- Record: 8W / 4L / 0T (12 battles)
- Rank: #15 of 68

### Pose & Character Mashup

- Elo: 1200
- Record: 10W / 3L / 0T (13 battles)
- Rank: #3 of 33

### The Capybara Taxi Driver

- Elo: 1193
- Record: 7W / 6L / 0T (13 battles)
- Rank: #11 of 69

### Chalkboard Menu

- Elo: 1192
- Record: 14W / 14L / 0T (28 battles)
- Rank: #10 of 69

### Apollo 11: Journey to Tranquility

- Elo: 1185
- Record: 5W / 4L / 0T (9 battles)
- Rank: #20 of 70

### Adorable Baby Animals in Sunny Meadow

- Elo: 1182
- Record: 7W / 9L / 0T (16 battles)
- Rank: #28 of 72

### The Reversed Rodeo

- Elo: 1179
- Record: 4W / 4L / 0T (8 battles)
- Rank: #8 of 68

### Man and Car in California

- Elo: 1174
- Record: 4W / 0L / 0T (4 battles)
- Rank: #14 of 35

### Outfit Transfer Challenge

- Elo: 1145
- Record: 3W / 5L / 1T (9 battles)
- Rank: #10 of 33

### Vintage Cafe Logo

- Elo: 1128
- Record: 3W / 9L / 0T (12 battles)
- Rank: #40 of 70

### Isometric Miniature Diorama Scenes

- Elo: 1106
- Record: 4W / 12L / 0T (16 battles)
- Rank: #50 of 72

### Fantasy Warrior

- Elo: 1106
- Record: 4W / 5L / 1T (10 battles)
- Rank: #46 of 71

### Modern Clean Menu

- Elo: 1070
- Record: 1W / 5L / 0T (6 battles)
- Rank: #54 of 69


## Use Cases & Category Performance

### Lighting, Shadows & Materials (Image Editing)

- Rank: #5 of 36
- Elo: 1250
- Record: 18W / 9L / 1T (28 battles)
- Win Rate: 64.3%

### Art (Text-to-Image)

- Rank: #8 of 57
- Elo: 1232
- Record: 14W / 5L / 0T (19 battles)
- Win Rate: 73.7%

### Preservation (Image Editing)

- Rank: #7 of 37
- Elo: 1221
- Record: 18W / 10L / 1T (29 battles)
- Win Rate: 62.1%

### Prompt Adherence (Image Editing)

- Rank: #7 of 29
- Elo: 1217
- Record: 13W / 9L / 1T (23 battles)
- Win Rate: 56.5%

### People & Poses (Image Editing)

- Rank: #7 of 27
- Elo: 1225
- Record: 11W / 3L / 0T (14 battles)
- Win Rate: 78.6%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #17 of 61
- Elo: 1230
- Record: 49W / 48L / 2T (99 battles)
- Win Rate: 49.5%

### Aesthetics (Image Editing)

- Rank: #11 of 33
- Elo: 1215
- Record: 5W / 0L / 0T (5 battles)
- Win Rate: 100.0%

### Adding & Editing Objects (Image Editing)

- Rank: #10 of 29
- Elo: 1210
- Record: 7W / 5L / 1T (13 battles)
- Win Rate: 53.8%

### Photorealism (Image Editing)

- Rank: #14 of 36
- Elo: 1214
- Record: 8W / 6L / 1T (15 battles)
- Win Rate: 53.3%

### Photorealism (Text-to-Image)

- Rank: #25 of 62
- Elo: 1203
- Record: 71W / 61L / 4T (136 battles)
- Win Rate: 52.2%

### Text Rendering (Text-to-Image)

- Rank: #26 of 61
- Elo: 1218
- Record: 53W / 60L / 2T (115 battles)
- Win Rate: 46.1%

### Portraits (Text-to-Image)

- Rank: #23 of 50
- Elo: 1171
- Record: 4W / 5L / 1T (10 battles)
- Win Rate: 40.0%

### Cartoon, Anime & Fantasy (Text-to-Image)

- Rank: #23 of 50
- Elo: 1171
- Record: 4W / 5L / 1T (10 battles)
- Win Rate: 40.0%

### 3D Imaging & Modeling (Text-to-Image)

- Rank: #30 of 61
- Elo: 1204
- Record: 15W / 16L / 1T (32 battles)
- Win Rate: 46.9%

### Prompt Adherence (Text-to-Image)

- Rank: #32 of 62
- Elo: 1226
- Record: 69W / 73L / 3T (145 battles)
- Win Rate: 47.6%

### Backgrounds & Scenes (Image Editing)

- Rank: #15 of 26
- Elo: 1206
- Record: 4W / 0L / 0T (4 battles)
- Win Rate: 100.0%

### Creativity (Text-to-Image)

- Rank: #39 of 62
- Elo: 1205
- Record: 30W / 35L / 1T (66 battles)
- Win Rate: 45.5%

### Aesthetics (Text-to-Image)

- Rank: #41 of 62
- Elo: 1213
- Record: 75W / 74L / 4T (153 battles)
- Win Rate: 49.0%


## Image Gallery

20 images available for this model. Browse all at https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/gallery

### Curated Examples

- [Cinematic wide shot of a sophisticated, high-end boutique storefront at dusk. The shop window is ...](https://assets.lumenfall.ai/21DXmWV9AX_Gf751UclKPTkkH_nCCINAi6JWjcUhmq4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/n4y1vvhfakobbard923hz6liyh77@jpeg)
- [A high-end cinematic close-up of a vintage 1950s camera lens reflecting a sun-drenched Italian co...](https://assets.lumenfall.ai/PkiWHEdS26cHPcm_9yBpaSXH5RgnEENPopBomEl3mGI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/z89mwfn35gzu0t4suxdnrn2korop@jpeg)
- [A hyper-realistic close-up of a weathered, vintage leather traveler's journal resting on a rustic...](https://assets.lumenfall.ai/qRBEPxku-A9MCAVoUgfrTW5esYaEyswBF4OcgTtQRks/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/9otlhkaizlrav8xejgv4qnn4kicw@jpeg)
- [A vintage wooden storefront for a bookstore called "THE TURNING PAGE" in crisp, elegant gold lett...](https://assets.lumenfall.ai/4NzFv1G_l8dxmIcKx501bL3VghvNWgwpX76A55jFdYY/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/pss6bd98sdf711lsyi5vu0d5ilfz@jpeg)

### Arena Competition Results

- [Geometric Composition](https://assets.lumenfall.ai/qmijruXwWEruLIGSvy83yyIGkKnmZIo0_1InbfVQzZM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/3nj7ldvbg3hgjq3vid3mu5s37rgn@jpeg): #4 of 70 (Elo 1270)
- [Magic Burger Explosion: Fiery Photorealism Challenge](https://assets.lumenfall.ai/CrmLH_fhypNL3dvWP8JBXRZwLsgXPf5kmk9iGQLbsPk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/9s6if1h1wvyr81f8r7wz49oekrcw@jpeg): #6 of 69 (Elo 1226)
- [The Halloween Invitation](https://assets.lumenfall.ai/5ZUI2eCuEoxH8EAM4hYfH4AaN7U0AXuuvgE-DMKZBtQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ar841ivv4hxqqilrf60jtac8k256@jpeg): #5 of 70 (Elo 1214)
- [Candid Street Photography](https://assets.lumenfall.ai/fsMx3gSnhYWupJn4F0zmUrdLjjjbAe-V0U0iOrvmmfQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/zm4k8jbaa0uj7pybjzwgcmwlw4tf@jpeg): #15 of 68 (Elo 1211)
- [Pose & Character Mashup](https://assets.lumenfall.ai/_8_giA4GhBmOd0y4BDYWBdnBu3AHJ236Vf-ojNN0bUo/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/j8xxq29wu8fp4zjg6b52q76pvayt@jpeg): #3 of 33 (Elo 1200)
- [The Capybara Taxi Driver](https://assets.lumenfall.ai/UhV5W-6LXgJoczWqoAXeGZSJmhUq9Ox2dtx9IOnwtA0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/d2c6nf0stvn2gte4wsa49g8o7imd@jpeg): #11 of 69 (Elo 1193)
- [Chalkboard Menu](https://assets.lumenfall.ai/C-2C3FBqdJDprlvZb3UQyKPc7YOpns_CjKylT6klOl0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/4pmfq033f7hhbd08upwqi18vwvs0@jpeg): #10 of 69 (Elo 1192)
- [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/Ds_XCz5cWYaSyGKkUjQTMSw4kvF7_vU79chKzjaiU3U/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/5e1a912p3ru4xebihogr6z7k42ci@jpeg): #20 of 70 (Elo 1185)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/2s1jwOOlYRjPQl6dgYCpWNzCbLNdW5NHWvdxEwfEivo/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/fgd6j244ts36tvr7i2jh0kf4bqbz@jpeg): #28 of 72 (Elo 1182)
- [The Reversed Rodeo](https://assets.lumenfall.ai/QJsncZYC_wRHRAjZCNY0Lhe0yjH4k8KOn1Ggiq4eU_k/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/yvl5li00ep4y6nrq5q7csnefpg5c@jpeg): #8 of 68 (Elo 1179)
- [Man and Car in California](https://assets.lumenfall.ai/vaK-L1l9mal8HBn64sbWBb5ycy4P1R5AYWbvZEAy4jo/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/jehfz26p04riq6qf5gcobpu32ons@jpeg): #14 of 35 (Elo 1174)
- [Outfit Transfer Challenge](https://assets.lumenfall.ai/BSvBEdqQ-305cNj3akrzidGjLUigLcm1jNtToh1rJ0A/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/69k8fulmmld865idj2lepyo2s2ae@jpeg): #10 of 33 (Elo 1145)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/hJLBWFZweKwlFpYxAWjXK6iKaDXrzLD338R-UtOEB28/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ktb6t2jl9gubcmph4cbpphslg4em@jpeg): #40 of 70 (Elo 1128)
- [Isometric Miniature Diorama Scenes](https://assets.lumenfall.ai/J0tisnTAaYsrfT7-QVYRMU60FF4cXDOhlMZ4RyaVKnc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/m9fp5slvjx9ywlcys87pt0dhx3po@jpeg): #50 of 72 (Elo 1106)
- [Fantasy Warrior](https://assets.lumenfall.ai/vV7bMML0K6UPAonjll0ho8PoJPqoWtOHuV4K0OzK30g/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ncso9alzk19xyb0mbo25gsf7afwc@jpeg): #47 of 71 (Elo 1106)
- [Modern Clean Menu](https://assets.lumenfall.ai/Eum2KRAO8t_ahDPp3qUmbCFE1wZJ-Gy4kphXZ_vkot4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/plscedhiea7vmycg6dzyetfolzfb@jpeg): #54 of 69 (Elo 1070)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A vintage wooden storefront for a bookstore called "THE TURNING PAGE" in crisp, elegant gold lettering on the window. A cozy interior is visible with floor-to-ceiling shelves. On the sidewalk bench, a capybara sits quietly reading a newspaper.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux.2-klein-9b",
    "prompt": "",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'flux.2-klein-9b',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="flux.2-klein-9b",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=flux.2-klein-9b" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'flux.2-klein-9b',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="flux.2-klein-9b",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## Frequently Asked Questions

### How much does FLUX.2 [klein] 9B cost?

FLUX.2 [klein] 9B starts at $0.006 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use FLUX.2 [klein] 9B via API?

You can use FLUX.2 [klein] 9B through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "flux.2-klein-9b". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer FLUX.2 [klein] 9B?

FLUX.2 [klein] 9B is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for FLUX.2 [klein] 9B?

FLUX.2 [klein] 9B supports images up to 2048x2048 resolution.

## Links

- Model Page: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b
- About: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/providers
- API Reference: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/api
- Benchmarks: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/benchmarks
- Use Cases: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/use-cases
- Gallery: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/gallery
- Playground: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-9b/playground
- API Documentation: https://docs.lumenfall.ai