Skip to main content
POST
/
api
/
v3
/
openai
/
reverse
/
{model}
/
{scene}
sora-2-pro (image to video)
curl --request POST \
  --url https://api.example.com/api/v3/openai/reverse/{model}/{scene}
This endpoint provides submit task functionality.

​
Request Parameter

curl --request POST \
  --url https://gptproto.com/api/v3/openai/reverse/sora-2-pro/image-to-video \
  --header 'Authorization: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sora-2-pro",
  "orientation": "portrait",
  "size": "large",
  "prompt": "She turns around and smiles, then slowly walks out of the frame.",
  "images": [
    "https://oss.heyoos.com/ai-draw/material/land-part1-default.png"
  ],
  "duration": 15,
  "character_url": "https://oss.heyoos.com/2025/11/11/fffe18ab440d4fadb16b4563c4cd18d1.mp4"
}'

{
  "error": {
    "message": "Invalid signature",
    "type": "401"
  }
}

​
Parameters

ParameterTypeRequiredDefaultDescription
modelstring✅ Yessora-2-proThe video generation model to use.
promptstring✅ Yes-The positive prompt for the generation.
imagesstring[]✅ Yes-Array of image URLs to use as reference for video generation.
sizestring✅ YessmallVideo size quality. Options: small, large. Only sora-2-pro supports high-definition (large). Note: large is not supported when duration is 25s.
orientationstring❌ NoportraitVideo orientation, does not support specific size control. Options: portrait, landscape.
durationinteger❌ No10The duration of the generated video in seconds. For sora-2: 10, 15. For sora-2-pro: 15, 25.
character_urlstring❌ No-Non-human IP video URL. Used for character reference in video generation.