# FLUX Dev

> A 12 billion parameter rectified flow transformer capable of generating images from text descriptions.

- **Provider**: replicate
- **Model ID**: black-forest-labs/flux-dev
- **Category**: image_generation
- **Credits**: 58 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `image` (string, optional): Input image for image to image mode. The aspect ratio of your output will match this image
- `aspect_ratio` (string, optional): Aspect ratio for the generated image (Default: `1:1`; Options: `1:1`, `16:9`, `21:9`, `3:2`, `2:3`, `4:5`, `5:4`, `3:4`, `4:3`, `9:16`, `9:21`)
- `num_outputs` (integer, optional): Number of outputs to generate (Default: `1`; Range: min: 1, max: 4)
- `seed` (integer, optional): Random seed. Set for reproducible generation
- `go_fast` (boolean, optional): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed. (Default: `True`)
- `megapixels` (string, optional): Approximate number of megapixels for generated image (Default: `1`; Options: `1`, `0.25`)
- `prompt_strength` (number, optional): Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image (Default: `0.8`; Range: min: 0, max: 1)
- `output_quality` (integer, optional): Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs (Default: `80`; Range: min: 0, max: 100)
- `disable_safety_checker` (boolean, optional): Disable safety checker for generated images. (Default: `False`)
- `output_format` (string, optional): Format of the output images (Default: `webp`; Options: `webp`, `jpg`, `png`)
- `guidance` (number, optional): Guidance for generated image (Default: `3`; Range: min: 0, max: 10)
- `prompt` (string, **required**): Prompt for generated image
- `num_inference_steps` (integer, optional): Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. (Default: `28`; Range: min: 1, max: 50)

## Example Request

```json
{
  "model": "black-forest-labs/flux-dev",
  "input": {
    "aspect_ratio": "1:1",
    "num_outputs": 1,
    "output_format": "webp",
    "go_fast": true,
    "guidance": 3.5,
    "megapixels": "1",
    "prompt_strength": 0.8,
    "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
    "output_quality": 80,
    "num_inference_steps": 28
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

flux, text-to-image, image-generation, image-to-image, black-forest-labs, popular

## Documentation

https://replicate.com/black-forest-labs/flux-dev