Skip to main content
POST
/
v1beta
/
models
/
{model_name}
:predictLongRunning
veo (video to video)
curl --request POST \
  --url https://api.example.com/v1beta/models/{model_name}:predictLongRunning
Gemini’s veo 3.1 fast generate preview for the video to video API. 
curl --location 'https://api.gptproto.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning' \
  --header 'x-goog-api-key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "instances": [
        {
            "prompt": "a cat",
            "video": {
                "uri": "https://generativelanguage.googleapis.com/v1beta/files/acwe2jipjo5j:download?alt=media"
            }
        }
    ],
    "parameters": {
        "resolution": "720p"
    }
}'

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

​
Parameters

​
Parameters

ParameterTypeRequiredDefaultDescription
instancesarray✅ Yes-An array of instances containing the video generation parameters The text prompt describing how to transform the video
videoobject✅ Yes-The source video information The URI of the source video file (must be a valid Google Cloud Storage or Generative Language API file URI)
parametersobject❌ No-Additional parameters for video generation The resolution of the output video. Options: 720p, 1080p