tools

Generate an AI video from a text prompt

Generate an AI video from a text prompt. Submits the render and returns a job_id immediately - poll get_video_status until it completes. Spends the account's prepaid video-credit wallet (NOT platform credits); pass max_charge_usd to cap how much a single call may spend. Video generation may be invitation-gated.

post/api/mcp/tools/generate_video

Request

  • Base URL: https://finestructure.ai
  • URL: https://finestructure.ai/api/mcp/tools/generate_video
  • Auth: HTTP bearer

Request body

promptstring required

The shot to render. Up to 4000 chars.

modelstring

Model id from list_media_capabilities. Default 'seedance-2'.

durationinteger

Seconds. Snapped to the model's allowed values.

resolutionstring

480p, 720p, or 1080p (model dependent). Default 480p.

aspect_ratiostring

auto, 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9. Default auto.

image_urlsstring[]

Up to 9 public https reference images (Seedance models only).

max_charge_usdnumber

Refuse the render if it would charge more than this. Strongly recommended for autonomous agents.

Response

Tool executed successfully

okboolean required
toolstring required
resultobject required

Changes

No recorded changes to this operation across all 2 revisions of this API.