Get a face detection

Fetches one face's details by ID (bounding box, assigned person, timestamps, thumbnail). Use when you already have a face_id.

face_idstring required

Face ID (with face_ prefix) to fetch. Carried by the entries of an asset's faces field (returned with include=faces).

library_idstring nullable

Library the face belongs to. Optional if the user has a single library; required when they have multiple.

includestring[] nullable

Opt-in expansion fields. See list_faces for supported values. Accepts multiple include= query params or a single comma-delimited value.

Response

Successful Response

idstring required

Unique face identifier with 'face_' prefix

asset_idstring required

ID of the asset containing this face

person_idstring nullable

ID of the person this face belongs to (if identified)

bounding_boxobject required

Face location as {x, y, w, h} coordinates in pixels

confidencenumber nullable

Detector confidence on a 0-1 scale; higher is more confident among faces detected under the same configuration (values are not comparable across detector generations). Null on legacy faces without a stored score and on manually added faces.

source'automatic' | 'manual' required

How this face was added: 'automatic' for detector-found faces, 'manual' for user-drawn face boxes.

timestamp_msinteger nullable

For video files, timestamp in milliseconds when face appears

asset_urlsobject nullable

Asset variants for this face: 'thumbnail' with face crop

created_atstring date-time required

When this face was detected and recorded

updated_atstring date-time required

When this face record was last updated

v64

Get a face detection

Path parameters

Query parameters

Response