Create a video
create_videoStarts rendering a video and spends its credits (refunded if it fails). Returns at once with an id: poll get_generation until it is completed.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>"
},
"name": "create_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Quality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead. | |
| image | No | Optional start image: base64 JPEG, PNG or WebP (a data: URL works), under 10 MB. | |
| model | No | A model id from list_models, instead of a tier. | |
| sound | No | Sound on or off, where the model has a switch. Quick always has sound. | |
| prompt | Yes | What to make, in plain words. @handles use the person's saved characters. | |
| duration | No | Seconds, from the model's durations (list_models). | |
| image_id | No | Optional start image already sent to POST /v1/uploads. | |
| resolution | No | e.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's. | |
| max_credits | No | Refuse instead of spending more than this many credits. | |
| aspect_ratio | No | Aspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1". | |
| photo_consent | No | Required with an image: true only if the person confirmed they have the right to use it and the people in it agree. | |
| idempotency_key | No | Retrying with the same key never creates twice. |