Skip to main content
Core.Today
|
RunwayFastHigh

Runway Gen-4 Image Turbo

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.

70 credits
per image โ€” flat rate regardless of resolution (720p/1080p)
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 โ€” easy to swap between the two
Seed support for reproducible generation

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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"
    ]
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes-Text prompt for image generation. Reference your images using @tag_name
seedintegerNo-Random seed. Set for reproducible generation
resolutionstringNo1080pImage resolution โ€” same price at either setting
720p1080p
aspect_ratiostringNo16:9Image aspect ratio
16:99:164:33:41:121:9
reference_tagsarrayNo[]An optional tag for each reference image, referenced in your prompt as @tag_name. Alphanumeric, starts with a letter, 3-15 characters
reference_imagesarrayNo[]You must give at least one reference image. Up to 3 are supported. Images must be between 0.5 and 2 aspect ratio

How to Provide File Input

There are 3 ways to provide files for the reference_images parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=runwayml/gen4-image-turbo" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:reference_images=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "runwayml/gen4-image-turbo",
  "input": {
    "prompt": "your prompt here",
    "reference_images": ["https://example.com/image.jpg"]
  }
}
See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Two Referenced Characters in a Scene

Two reference images bound to @woman and @man tags

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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"
    ]
  }
}'

Tips & Best Practices

1Unlike Gen-4 Image, at least one reference image is required โ€” this is a reference-driven model, not plain text-to-image
2Pricing is flat (90 credits), so always pick 1080p โ€” there is no cost saving at 720p
3Use Turbo for iteration volume and switch the same request to Gen-4 Image when you need maximum fidelity
4Tag every reference and mention it as @tag_name in the prompt for precise control
5Only use photos of real people as references with the person's explicit consent

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