OpenAISlowUltra

OpenAI Sora 2

OpenAI's video generation model with realistic physics simulation and audio generation capabilities, producing highly coherent videos.

930 credits

per video

Realistic physics simulation

Audio generation support

Up to 20-second videos

Multiple resolution options (480p-1080p)

Image-to-video with start frame

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

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": "openai/sora-2",
  "input": {
    "prompt": "A glass marble rolls down a wooden ramp, bounces off the table edge, and splashes into a glass of water, slow motion, photorealistic",
    "duration": "10",
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text description of the video to generate
`openai_api_key`	string	No	-	Optional: Your OpenAI API key. If you use your own OpenAI API key, you will be charged directly by OpenAI.
`input_reference`	string	No	-	An optional image to use as the first frame of the video. The image must be the same aspect ratio as the video.
`seconds`	integer	No	4	Duration of the video in seconds 4812
`aspect_ratio`	string	No	portrait	Output aspect ratio portraitlandscape

How to Provide File Input

There are 3 ways to provide files for the input_reference 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=openai/sora-2" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:input_reference=@your_file.png"

Image URL

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

{
  "model": "openai/sora-2",
  "input": {
    "prompt": "your prompt here",
    "input_reference": "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.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Physics Simulation

Realistic physics-based video

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "openai/sora-2",
  "input": {
    "prompt": "A glass marble rolls down a wooden ramp, bounces off the table edge, and splashes into a glass of water, slow motion, photorealistic",
    "duration": "10",
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }
}'

Urban Timelapse

Dynamic city timelapse video

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "openai/sora-2",
  "input": {
    "prompt": "Timelapse of a busy city intersection from sunset to night, car light trails, pedestrians moving quickly, cinematic wide angle",
    "duration": "15",
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}'