Video Generation API

Supported models

Pick any model slug from the table and pass it as model in the request body. All video models share the same endpoint shape.

Endpoint

POST https://aimarcusimage.eu/api/v1/jobs/createTask

Request

curl https://aimarcusimage.eu/api/v1/jobs/createTask \
  -H "Authorization: Bearer sk-aig-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google-google-veo-3-1-text-to-video-fast-1080p",
  "input": {
    "prompt": "a golden retriever running through autumn leaves, cinematic",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}'

Response

{
  "code": 200,
  "data": {
    "taskId": "task_01j..."
  }
}

Video generation is async. Poll GET /api/v1/jobs/recordInfo?taskId=... every 3-5 seconds, or set up a webhook.

Poll task status

curl https://aimarcusimage.eu/api/v1/jobs/recordInfo?taskId=task_01j... \
  -H "Authorization: Bearer sk-aig-YOUR_KEY"

Next steps