Are you an LLM? Read llms.txt for a summary of the docs, or llms-full.txt for the full context.
Skip to content

Face Liveness Detection

Checks that a selfie shows a live person, not a printed photo, a screen or a mask.

SlugIDStatusTaggedModel version
face-liveness-detection7ActiveYesv2

What it detects

DetectsDoes not detect
Presentation attacks: printed photos, screen replays and masks held up to the cameraAI-generated or face-swapped faces. Use ekyc-deepfake or ai-image-detection for those

Request

SlotAccepted contentType
originalimage/jpeg, image/png
{
  "taskTypeId": "7",
  "inputs": [
    { "slotName": "original", "fileName": "selfie.jpg", "contentType": "image/jpeg", "sizeBytes": 262144 }
  ]
}

See Running a job for the full create, upload and finalize flow.

Limits

  • File size: up to the account upload limit, 10 MB by default.
  • Send a photo where the face fills most of the frame; the image is scaled down to 224 × 224 pixels for analysis.

Result

Uses the standard result fields. Here "fake" means spoofed: isFake is true when the capture is not a live person.

{
  "isFake": true,
  "confidencePercent": 89.96,
  "fakeConfidencePercent": 89.96,
  "realConfidencePercent": 10.04,
  "tag": "fake",
  "tagBoundaries": { "real": 30, "likelyReal": 50, "likelyFake": 75 },
  "modelVersion": "v2"
}

Output artifacts

kindFileDescription
resultresult.jsonThe liveness result

Cost and availability

  • Fixed price per job, set by your plan. The exact amount is returned as cost when you create the job. See Quotas & Credits.
  • Available on the cloud API; your plan decides which task types you can use.