# FLUX.2 Klein 9B - Core.Today AI API

> 4-step distilled FLUX.2 [klein] 9B — fast, higher-capacity sibling of Klein 4B for text-to-image generation and multi-reference image editing (up to 5 input images), with selectable output megapixels.

- **Provider**: Black Forest Labs
- **Model ID**: black-forest-labs/flux-2-klein-9b
- **Category**: Image Generation
- **Credits**: 35 per image at 1MP (default); 9 at 0.25MP, 18 at 0.5MP, 70 at 2MP, 140 at 4MP
- **Speed**: Fast
- **Quality**: High

## Features
- 4-step distilled 9B model — sub-second to few-second inference
- Text-to-image and multi-reference image editing (up to 5 images)
- Selectable output resolution from 0.25MP to 4MP
- go_fast optimizations on by default
- Billed by output megapixels, so small previews cost less

## Use Cases
- Near real-time image generation in interactive apps
- Reference-guided edits combining up to 5 images
- Low-cost drafts before a final high-resolution render
- High-throughput batch generation pipelines

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for image generation

### Optional
- **images**: array (default: []) - Input images for image-to-image generation (max 5; jpeg, png, gif or webp)
- **aspect_ratio**: string (default: 1:1) - Aspect ratio for the generated image. Use match_input_image to match the first input image
  Options: 1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 21:9, 9:21, match_input_image
- **megapixels**: string (default: 1) - Resolution of the output image in megapixels. Higher values cost more credits
  Options: 0.25, 0.5, 1, 2, 4
- **seed**: integer - Random seed. Set for reproducible generation
- **go_fast**: boolean (default: true) - Run faster predictions with additional optimizations
- **output_format**: string (default: jpg) - Format of the output images
  Options: webp, jpg, png
- **output_quality**: integer (default: 95) - Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
- **disable_safety_checker**: boolean (default: false) - Disable safety checker for generated images.

## Examples

### 1MP Generation (Default)
Default 1-megapixel text-to-image generation with in-image text — 35 credits
```json
{
  "model": "black-forest-labs/flux-2-klein-9b",
  "input": {
    "images": [],
    "prompt": "A surreal cosmic garden scene with bioluminescent flora against a deep navy blue to black background, glowing particles floating like plankton, cinematic lighting. With large white text in the center \"FLUX.2 [klein] 9B\"",
    "go_fast": true,
    "megapixels": "1",
    "aspect_ratio": "1:1",
    "output_format": "jpg",
    "output_quality": 95
  }
}
```

### Low-Cost Preview
0.25-megapixel draft for quick prompt iteration — 9 credits
```json
{
  "model": "black-forest-labs/flux-2-klein-9b",
  "input": {
    "prompt": "A neon-lit cyberpunk alley at night, concept sketch",
    "megapixels": "0.25"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- megapixels directly sets the price tier — use 0.25-0.5MP for previews and 2-4MP only for final renders
- Supply up to 5 reference images via images to guide edits; use aspect_ratio match_input_image to keep the first image's framing
- go_fast is on by default; turn it off only if you see quality issues
- Pick 4B for the lowest cost and 9B when you need more detail and prompt fidelity

## Documentation
https://replicate.com/black-forest-labs/flux-2-klein-9b