API contract reference. Production biometric endpoints currently return 503; example thresholds, SDK calls and performance figures are not release approval. Try the separately protected private comparison demo.

Documentation

PaxLI V1 Documentation

PaxLI is a biometric verification engine focused on calibrated matching, quality gating, and presentation attack detection. It stores zero government ID records and leaves billing and identity policy to your application.

Deterministic Decision States

Every stage in the pipeline fails safely. If image quality is below q_min = 40.0, or a model is unavailable, PaxLI never guesses or defaults to MATCH.

MATCH

Quality passed, liveness passed (when requested), and similarity >= calibrated threshold.

NO_MATCH

Quality and liveness passed, but similarity fell below the calibrated threshold.

INCONCLUSIVE

Frame failed quality gating (e.g. BLURRY, TOO_DARK) or liveness fell in the uncertain band. Safe to retry.

REJECT

Presentation attack detected (SPOOF_SUSPECTED / PAD_FAILED) or multi-view 3D check flagged a tilted photo.

Calibration Profiles

Instead of guessing magic cosine similarity numbers, choose a profile calibrated against your embedder and capture type (selfie_selfie, selfie_id, or multiview).

ProfileTarget FARExample ThresholdRecommended For
strict0.01% FAR (1 in 10,000)0.562High-value account recovery, privileged access, financial step-up.
standard0.1% FAR (1 in 1,000)0.452Default onboarding, selfie-to-ID checks, workforce sign-in.
relaxed1.0% FAR (1 in 100)0.348Low-friction convenience re-authentication paired with active liveness.