Analyze video for visual safety concerns across extracted frames
Upload a video file (mp4, webm, quicktime, avi — max 100MB, max 10 min). Extracts key frames at even intervals and runs vision analysis on each frame. Returns per-frame results, flagged timestamps, and an aggregated overall risk score. Ideal for moderating uploaded video content, screen recordings, and video messages.
Authorizations
API key as Bearer token
Response
Default Response
none, low, medium, high, critical A concern was observed at ANY severity, including monitor-only cases. For production branching prefer recommended_action.
Confidence in the overall verdict (0-1), from the frame that drove it.
Routing key, weakest to strongest: none, monitor, flag_for_review, block, immediate_intervention. Safe to switch on. A video whose frames could not be decoded returns flag_for_review, never none.
none, monitor, flag_for_review, block, immediate_intervention Human-readable expansion of recommended_action for a moderator UI. Free text: do not branch on it.
Why this verdict was reached. Built from category and severity labels only; never contains the frame descriptions.
Number of credits consumed by this request
Per-call override of account incident logging: "true" forces persistence, "false" suppresses it. Omit for account default.
Echo of the metadata you provided in the request