Face Compare
Send two images and get back a similarity score, a match flag and the threshold it was judged against.
Send two images and get back a similarity score, a match flag and the threshold it was judged against. Both faces are turned into 512-dimensional ArcFace embeddings and compared by cosine distance, which is why it works across lighting, angle and age gap rather than matching pixels.
The usual job is checking that a selfie belongs to the same person as a document photo, or that a returning user is who they were last time. Nothing is stored: the images are processed for the call and dropped, so there is no gallery accumulating faces and nothing to delete later.
It returns a MEASUREMENT, not a decision. Where the threshold sits is yours to choose — a payments flow and a photo-library grouping want very different answers from the same score, and only you know which mistake costs more.
Call it
The first response is 402 with the exact price and every rail you can
pay with. Pay, repeat the request with the proof, and you get the result.
curl -X POST https://api.glianalabs.com/v1/tools/face-compare \
-H 'content-type: application/json' \
-d '{"a":{"image_url":"https://example.com/a.jpg"},"b":{"image_url":"https://example.com/b.jpg"}}'When to use it
Compare two faces and score how alike they are. Use when an agent checks whether a selfie matches a document photo or a previous image. Inputs: a and b, each { image_url | image_base64 } (both required). Returns similarity (cosine, 0-1), match, and the threshold it was measured against. NO LIVENESS CHECK — a photograph of a photograph can match, so treat the score as a signal for your own decision, not proof of identity. Nothing is stored.
What it costs
$0.0110 per successful call — flat, with no plan, minimum or monthly fee. A call that fails validation is refused before it runs, so it is never charged.
Not sure this is the right endpoint? GET /v1/consult?intent=… is
free and answers that.
Often used with this
Face Detect
$0.0030Find faces in an image. Use when an agent counts people, checks a photo contains exactly one face before a match, or estimates age and gender.
Face Embed
$0.0060Turn every face in an image into a 512-d ArcFace vector.
KYC Verify
$0.0150One request takes an identity document and a selfie and returns the fields it read from the document alongside a face-similarity score between the two.