Skip to main content
POST
/
v3
/
videos
Generate a video
curl --request POST \
  --url https://api.opper.ai/v3/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>"
}
'
{
  "id": "<string>",
  "status_url": "<string>"
}
Video generation is asynchronous. This call validates the request, starts the job, and returns 202 Accepted with an id and a status_url — it does not block until the video is ready. The flow is:
  1. POST /v3/videos with model + prompt → 202 { id, status_url }
  2. Poll GET {status_url} (i.e. GET /v3/artifacts/{id}/status) until status is completed or failed
  3. On completed, download the video from the presigned url (valid for one hour)
See the Video quickstart for the end-to-end flow with runnable snippets, and List video models to discover available models and their parameters.

​
Parameters

model and prompt are the only fields Opper owns. Everything in parameters is forwarded verbatim to the provider, which validates and rejects it — so the accepted keys depend on the model (e.g. Sora takes seconds/size; Veo takes durationSeconds/resolution/generateAudio). Use GET /v3/videos/models to see each model’s supported aspect_ratios, resolutions, and max_duration. For image-to-video and video-to-video, pass a top-level image or video (an http(s) URL or data-URI) with a model whose capabilities include image_to_video or video_editing. Accepted source formats differ per provider: Sora takes a URL or base64 (image dims must equal size); Veo takes base64/data-URI or gs:// (not an http URL); Pruna and xAI require a public, server-fetchable URL. See the Video quickstart.

Authorizations

​
Authorization
string
header
required

API key authentication. Pass your API key as a Bearer token.

Body

application/json
​
model
string
required
​
prompt
string
required
​
parameters
object

Response

Successful response

​
id
string
required
​
status_url
string
required