Start building

Flux 2 Klein 9b

bfl/flux-2/klein/9b/base

Flux 2 Klein 9b by BFL - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.

Use in agentGet API key
Base price
$0.01USD / run
Execution
async
Model type
image
Input fields
6

Try the model

Playground

Open playground
Input
The prompt to generate an image from.
020
Guidance scale for classifier-free guidance. Range: 0 to 20.
450
The number of inference steps to perform. Range: 4 to 50.
The format of the generated image. Allowed values: jpeg, png.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The seed to use for the generation. If not provided, a random seed will be used.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.01 / run

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
BFL
Model ID
bfl/flux-2/klein/9b/base
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Flux 2 Klein 9b

Flux 2 Klein 9b exposes the FLUX.2 Klein 9B Base capability for compact image generation. The undistilled Base architecture retains full training signal and higher output diversity for adaptation and research.

Use this 9B route when a stronger quality-to-speed balance and more complex visual understanding matter. Write a detailed narrative prompt because Klein does not depend on automatic prompt upsampling. Choose the Base form for fine-tuning or diverse research outputs rather than minimum inference latency.

Highlights

  • FLUX.2 Klein 9B Base architecture. Uses the undistilled 9B foundation with full training signal and diverse output behavior.
  • Detailed image generation. Creates coherent photographic and designed imagery from narrative prompts.
  • Expanded visual capacity. Uses the larger Klein variant for more complex concepts and a stronger quality-speed balance.
  • Fine-tuning foundation. Provides an adaptable starting point for LoRA training, full fine-tuning, and research.

Pricing

ConfigurationBilling unitPrice
Base generationPer request$0.015

When to Use

✅ Good fit❌ Consider alternatives
The project needs this exact generation or editing routeThe intended task belongs to video, audio, or 3D media
Available references match every required local fieldRequired source assets or rights are unavailable
The brief can specify composition, color, and finishOutput must be deterministic at pixel level
Supported dimensions and formats fit final placementDelivery requires unsupported canvas specifications
An asynchronous generated image fits productionA live frame-synchronous response is mandatory

Prompt Guide

Write a complete visual brief: identify the subject and references, define composition and viewpoint, describe lighting, palette, materials, typography, and finish, then list exact preservation constraints. FLUX.2 Klein does not rely on prompt upsampling, so use clear descriptive sentences rather than sparse keywords.

{
  "prompt": "A photorealistic editorial composition with precise subject placement, controlled lighting, exact colors, and clean typography",
  "seed": 1,
  "aspect_ratio": "21:9",
  "output_format": "jpeg"
}

Technical Specs

SpecValue
Model IDbfl/flux-2/klein/9b/base
Input fieldsseed (integer)<br>prompt (string)<br>aspect_ratio (string; 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16)<br>output_format (string; jpeg, png)<br>guidance_scale (number; 0–20)<br>num_inference_steps (integer; 4–50)
Required inputprompt
Output fieldsurl, content_type
ExecutionAsynchronous job

Related Models

  • bfl/flux-2/klein/4b
  • bfl/flux-2/klein/4b/base
  • bfl/flux-2/klein/4b/base/edit

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
bfl/flux-2/klein/9b/base
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-2/klein/9b/base",
  "prompt": "A cyberpunk samurai standing in neon-lit Tokyo street at night, rain-soaked pavement reflecting holographic advertisements in pink and blue, steam rising from street vents, wearing futuristic armor with glowing accents, cinematic composition, Unreal Engine 5 quality, ray-traced reflections, shallow depth of field, hyper-detailed",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 5,
  "num_inference_steps": 28
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Flux 2 Klein 9bThis model
BFL		———Jan 15, 2026
FLUX Virtual Try-On
BFL		———May 28, 2026
Flux Pro Erase
BFL		———May 21, 2026
Flux 2 Pro
BFL		———May 14, 2026
FLUX.2 [klein] 9B LoRA
BFL		———Mar 17, 2026
FLUX.2 [klein] 9B LoRA
BFL		———Mar 17, 2026