# Runway Gen-4 Image Turbo - Core.Today AI API

> Gen-4 Image Turbo is 2.5x faster and cheaper than Gen-4 Image, with the same reference-driven API: use 1 to 3 reference images with @tag mentions for consistent characters and objects, at a flat price regardless of resolution.

- **Provider**: Runway
- **Model ID**: runwayml/gen4-image-turbo
- **Category**: Image Generation
- **Credits**: 70 per image — flat rate regardless of resolution (720p/1080p)
- **Speed**: Fast
- **Quality**: High

## Features
- 2.5x faster and cheaper than Gen-4 Image
- Flat 90-credit price for both 720p and 1080p
- 1 to 3 reference images with @tag_name prompt mentions (at least 1 required)
- Same API surface as Gen-4 Image — easy to swap between the two
- Seed support for reproducible generation

## Use Cases
- High-volume consistent-character generation on a budget
- Rapid iteration and draft exploration before a Gen-4 Image final pass
- Product variations placing the same referenced item in new scenes
- Social content pipelines that need fast turnaround
- A/B testing prompt variations with the same references

## 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. Reference your images using @tag_name

### Optional
- **seed**: integer - Random seed. Set for reproducible generation
- **resolution**: string (default: 1080p) - Image resolution — same price at either setting
  Options: 720p, 1080p
- **aspect_ratio**: string (default: 16:9) - Image aspect ratio
  Options: 16:9, 9:16, 4:3, 3:4, 1:1, 21:9
- **reference_tags**: array (default: []) - An optional tag for each reference image, referenced in your prompt as @tag_name. Alphanumeric, starts with a letter, 3-15 characters
- **reference_images**: array (default: []) - You must give at least one reference image. Up to 3 are supported. Images must be between 0.5 and 2 aspect ratio

## Examples

### Two Referenced Characters in a Scene
Two reference images bound to @woman and @man tags
```json
{
  "model": "runwayml/gen4-image-turbo",
  "input": {
    "prompt": "a close up portrait of @woman and @man driving fast in a red 1980s sports car",
    "resolution": "1080p",
    "aspect_ratio": "4:3",
    "reference_tags": [
      "woman",
      "man"
    ],
    "reference_images": [
      "https://example.com/woman.jpg",
      "https://example.com/man.jpg"
    ]
  }
}
```

## 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
- Unlike Gen-4 Image, at least one reference image is required — this is a reference-driven model, not plain text-to-image
- Pricing is flat (90 credits), so always pick 1080p — there is no cost saving at 720p
- Use Turbo for iteration volume and switch the same request to Gen-4 Image when you need maximum fidelity
- Tag every reference and mention it as @tag_name in the prompt for precise control
- Only use photos of real people as references with the person's explicit consent

## Documentation
https://replicate.com/runwayml/gen4-image-turbo