# Imagen 4 - Core.Today AI API

> Google's Imagen 4 flagship text-to-image model.

- **Provider**: Google
- **Model ID**: google/imagen-4
- **Category**: Image Generation
- **Credits**: 93 per image (flat, regardless of 1K/2K image_size)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Google's flagship Imagen 4 quality tier
- 1K and 2K output resolution at the same flat price
- Configurable safety filter strictness
- Broad aspect ratio support for social and print formats
- Strong photorealism and detail fidelity

## Use Cases
- High-fidelity photorealistic image generation
- Marketing and social media visuals at 2K resolution
- Content requiring configurable safety filtering
- General-purpose flagship-quality text-to-image needs

## 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
- **aspect_ratio**: string (default: 1:1) - Aspect ratio of the generated image
  Options: 1:1, 9:16, 16:9, 3:4, 4:3
- **image_size**: string (default: 1K) - Resolution of the generated image. Billed the same regardless of tier
  Options: 1K, 2K
- **safety_filter_level**: string (default: block_only_high) - block_low_and_above is strictest; block_only_high is most permissive
  Options: block_low_and_above, block_medium_and_above, block_only_high
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png

## Examples

### Cinematic Portrait
A late-90s indie film style cinematic portrait
```json
{
  "model": "google/imagen-4",
  "input": {
    "prompt": "The photo: Create a cinematic, photorealistic medium shot capturing the nostalgic warmth of a late 90s indie film.",
    "aspect_ratio": "16:9",
    "safety_filter_level": "block_medium_and_above"
  }
}
```

## 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
- Choose image_size=2K freely — the price is flat regardless of 1K or 2K
- Loosen safety_filter_level to block_only_high (default) only when content is not sensitive
- Use google/imagen-4-fast instead when speed and cost matter more than maximum quality
- aspect_ratio choices are optimized for common social and print formats

## Documentation
https://replicate.com/google/imagen-4