
Anti-spoofing detection for biometric authentication (iBeta Level 1)
Face anti-spoofing for biometric authentication (requires 8 frames for temporal analysis)
video_urlstringURL of video for liveness detection (preferred)
https://example.com/selfie.mp4image_urlstring|arraySingle video URL or array of 8 frame images
https://example.com/video.mp4Liveness detection result with attack type identification
is_realbooleanTrue if real face detected (liveness pass)
trueis_spoofbooleanTrue if presentation attack detected
falsereal_probabilityfloatConfidence that face is real (0.0-1.0)
0.98confidencefloatOverall detection confidence (0.0-1.0)
0.95attack_typeintegerNumeric attack type code
0attack_type_namestringHuman-readable attack type
realattack_type_confidencefloatConfidence in attack type classification
0.92{
"model": "face-liveness",
"video_url": "https://example.com/selfie.mp4"
}{
"inference_id": "inf_xyz789abc123def456",
"model_id": "face_liveness",
"model_name": "Face Liveness Detection",
"moderation_type": "video",
"status": "completed",
"result": {
"is_real": true,
"is_spoof": false,
"real_probability": 0.98,
"confidence": 0.95,
"attack_type": 0,
"attack_type_name": "real",
"attack_type_confidence": 0.92
},
"response_time_ms": 2100,
"created_at": "2026-02-01T10:54:35Z",
"completed_at": "2026-02-01T10:54:37Z"
}429 HTTP error code along with an error message. You should then retry with an exponential back-off strategy, meaning that you should retry after 4 seconds, then 8 seconds, then 16 seconds, etc.Integrate Face Liveness Detection into your application today with our easy-to-use API.