PRODUCTS

Five checks. Take them together or one at a time.

Every module runs on its own and is priced on its own. You assemble the flow you actually need — you never pay for a check you did not use.

DOCUMENT VERIFICATION

Read every field. Trust none of them blindly.

Our in-house OCR model reads document fields with high confidence, while the MRZ is decoded via a separate path calibrated for OCR-B. ICAO 9303 check digit validation, cross-field consistency checks and ELA (Error Level Analysis) tamper detection; blur and brightness quality gates reject poor captures upfront.

In-house OCRICAO 9303ELAMRZ / OCR-B

Price: ID Verification $0.15

9:412 / 5

Scan the front of your ID

Place the document in the frame; the card is detected and cropped automatically.

align document
Capturing…

Secured by

LIVENESS DETECTION

Is that a screen, a print, or a person?

Three layers of assurance: server-verified active challenges (blink, head turn), passive anti-spoofing with our in-house model (trained to catch print, screen replay and moiré artifacts), and texture and colour checks that flag screens and printouts. A nonce + TTL mechanism blocks replay attacks.

In-house anti-spoofingLBP / FFT / YCrCbNonce + TTL

Price: Passive Liveness $0.05 · Active Liveness $0.05

9:413 / 5

Look at the camera

Follow the on-screen prompts — you may be asked to blink or turn your head.

face
Checking liveness…

Secured by

FACE MATCHING

Is the face on the document the face in front of the camera?

Our in-house face model biometrically compares the document photo against the liveness selfie; faces with low detection scores (blurry/partial) are rejected at a quality gate. Every approved face is kept for comparison — if the same face re-enrolls under a different identity, a duplicate signal is raised.

In-house face modelpgvector

Price: Face Match (1:1) $0.05 · Face Search (1:N) Free

Face matchingMatched
Document photo
Liveness selfie
0.87Similaritythreshold 0.70
Duplicate search0 hits

AML SCREENING

A match is a flag, not a decision.

OFAC SDN, UN Consolidated, EU FSF and UK Sanctions List sanctions lists are synced daily. Names are normalized and screened with fuzzy, token-based matching; date-of-birth mismatches automatically eliminate false positives. No match ever auto-rejects — the decision is always left to a human.

OFAC SDNUN ConsolidatedEU FSFUK Sanctions List

Price: AML Screening $0.20

AML screening1 hit
ApplicantList entry
ADÉOLA OKONKWOFull nameADEOLA OKONKWOFull name
1990-01-01Date of birth1974-06-18Date of birth
NGACountryNGACountry
OFAC SDNGoes to a human — never an automatic rejection

AI REVIEW ASSISTANT · POWERED BY CLAUDE

A second pair of eyes for your analysts, never the final say.

For every session routed to manual review, Claude drafts a note for the analyst from the check results: a short summary, which signal is suspicious and why, a suggested action (approve, reject or request resubmission) and, for AML hits, why the match may be a false positive. Only scores, check codes and flags reach the model, never images, biometrics or personal data. The decision always stays with a human.

Opt-in per customer account. Each suggestion is stored next to the analyst's final decision, so you can see how often it helped.

Sent to the model
  • Check names, results and reason codes
  • Scores and the platform's thresholds
  • Duplicate-face counts and AML comparison signals
Never sent
  • Document images and selfies
  • Face templates and NFC chip data
  • Names, dates of birth and document numbers

Ready to integrate?

Get in touch for a sandbox environment, API keys and integration documentation.