Verify any face. Without asking them to do anything.
Prove the person on camera is real and live. iBeta-certified anti-spoof — defeats deepfakes, masks, replays, and morph attacks in sub-2 seconds. Passive at $0.10, active at $0.15. 500 free/month.
Catch 3D masks, deepfakes, replay attacks, and printed photos.
iBeta-certified, sub-2-second verdict, $0.10 per check, 500 free every month.
How it works
From sign-up to verified user in four steps.
Step 01
Create the workflow
Pick the checks you want — ID, liveness, face match, sanctions, address, age, phone, email, custom questions. Drag them into a flow in the dashboard, or post the same flow to our API. Branch on conditions, run A/B tests, no code required.
Step 02
Integrate
Embed natively with our Web, iOS, Android, React Native, or Flutter SDK. Redirect to a hosted page. Or just send your user a link — by email, SMS, WhatsApp, anywhere. Pick what fits your stack.
Step 03
User goes through the flow
Didit hosts the camera, the lighting cues, the mobile hand-off, and accessibility. While the user is in the flow, we score 200+ fraud signals in real time and verify every field against authoritative data sources. Result in under two seconds.
Step 04
You receive the results
Real-time signed webhooks keep your database in sync the moment a user is approved, declined, or sent to review. Poll the API on demand. Or open the console to inspect every session, every signal, and manage cases your way.
Built for developers · Built against fraud · Open by design
Six capabilities. One feature flag. LIVENESS.
Every capability below is a toggle on the same module. No upsell tiers, no separate SKUs, no add-on calls. Switch them on per workflow in the console, or pass them inline on the standalone endpoint.
Three methods on one module. Passive (one frame, zero user action) for low-friction sign-up. 3D Flash (a short light sequence captures depth from reflection) for higher-value passive flows. 3D Action & Flash (motion + flash) for regulator-sensitive markets and large-value onboarding.
Liveness method
Same JSON · Same workflow
LIVENESS
Auto
Passive1 frame
Flash
3D FlashFlash burst
Turn head
3D ActionMotion + flash
FrictionLowest
CoveragePAD L1
Use caseRegulator
02 · Certified anti-spoof
Tested against the full presentation-attack catalogue.
Independently tested and iBeta-certified — the standard NIST and the Open Identity Exchange cite. Blocks printed photos, screen replays, paper masks, silicone masks, latex masks, morph attacks, and AI-generated deepfakes. Re-tested annually as the attack catalogue grows.
PAD certification
ISO/IEC 30107-3 · Re-tested annually
iBeta L1
Presentation Attack Detection
Level 1 · Certified
NIST cited
Printed photoBlocked
Screen replayBlocked
Paper maskBlocked
Silicone maskBlocked
Morph attackBlocked
AI deepfakeBlocked
03 · Sub-2-second verdict
End-to-end inference in under two seconds.
Edge-served inference. No model download, no on-device acceleration assumption, no degraded experience on entry-level Android. Passive completes in under a second on most devices. Flash adds ~600ms. Active 3D adds ~1.5s — still sub-2 end to end.
Inference latency
Edge-served · p95 across all methods
< 2s
0.8s
Passive p95
1.4s
3D Flash p95
1.9s
3D Action p95
Passive820 ms
3D Flash1,420 ms
3D Action1,910 ms
Budget · 2,000 ms end-to-endedge · no model download
04 · Warnings
Tunable risk policy per workflow.
Seven configurable warnings — low score, possible duplicate, duplicate face, multiple faces, low face quality, low light, high light — each mapped to decline, review, or approve per application. Three auto-decline triggers (no face, attack detected, blocklisted face) stay enforced no matter what.
Risk policy
3 enforced · 2 tunable · per workflow
5 codes
Warning codeAction
NO_FACE_DETECTEDEnforced
Decline
LIVENESS_FACE_ATTACKEnforced
Decline
FACE_IN_BLOCKLISTEnforced
Decline
LOW_LIVENESS_SCORE
Review
LOW_FACE_LUMINANCE
Approve
05 · Age estimation
One capture, two signals.
Toggle Age Estimation on a liveness workflow and the same selfie returns a liveness verdict plus an estimated age band. Built for UK Online Safety Act and EU age-gating — real-human-AND-old-enough without putting a user through ID upload. $0.10 per check.
Selfie analysis
POST /v3/passive-liveness/
Liveness + Age
Single capture
liveness
Approved
score 98
age_estimation
24 yrs
band 18 – 29
method
passive
single frame
cost
$0.20
0.10 + 0.10
Ready · UK Online Safety Act · CCPA Age-Appropriate
06 · Biometric authentication
The same engine you use at sign-up. Now at every login.
Liveness is the foundation for Biometric Authentication — reuse the same anti-spoof model to verify returning users at every sensitive action: high-value transfer, password reset, large withdrawal. $0.10 per auth, drop-in for SMS 2FA, no carrier bill, no SIM-swap exposure.
Biometric authentication
POST /v3/session/
Face auth
High-value transfer
$12,400.00 · usr_4d2b6e1
Step-up
Face match vs enrollment0.42 sPass
Passive liveness — real human0.81 sPass
Risk policy applied0.05 sVerifying
Webhook fired · biometric_auth.passed · $0.101.28 s
Integrate
Two endpoints. Same JSON. Same price.
Create a session when you want our hosted UI to handle capture (required for active methods), or call the standalone passive endpoint when you already have the selfie. Both return the same liveness report.
You own the capture. We return the verdict inline.docs →
Agent-ready integration
Ship Liveness in one prompt.
Paste the block below into Claude Code, Cursor, Codex, Devin, Aider, or Replit Agent. Fill in the my_stack placeholder with your framework, language, and use case. The agent provisions Didit, builds the workflow with Liveness enabled, wires the webhook, and ships.
didit-integration-prompt.md
# Didit Liveness — integrate in 5 minutes
You are integrating Didit's Liveness (presentation-attack detection) module
into <my_stack>. Follow these steps exactly. Every URL, header, and enum
value below is canonical — do not paraphrase or "improve" them.
## 1. Provision an account
- Sign up: https://business.didit.me (no credit card required).
- Or provision programmatically: POST https://apx.didit.me/auth/v2/programmatic/register/
(returns an API key bound to the workspace + application).
## 2. Two integration paths — pick one
### Path A — Workflow Builder (hosted UI)
Best when you want Didit to handle camera, motion prompts, low-light
fallback, mobile handoff, and accessibility for you.
1. Create a workflow that contains the LIVENESS feature:
POST https://verification.didit.me/v3/workflows/
Authorization header: x-api-key: <your-api-key>
Body: workflow_label, features array with the single entry
{ feature: "LIVENESS" } (UPPERCASE — strict enum)
Optional config: liveness_method ("PASSIVE" | "FLASHING" | "ACTIVE_3D")
and per-warning threshold overrides.
2. Create a verification session for an end user:
POST https://verification.didit.me/v3/session/
Body: workflow_id (from step 1), vendor_data (your own user id).
Response: session_url — redirect the user to it.
3. Listen for webhook callbacks (see "Webhooks" below).
### Path B — Standalone server-to-server API
Best when you already have a selfie image (mobile SDK capture, native
onboarding app, reseller pipeline). Standalone is single-frame
PASSIVE only — for ACTIVE_3D or FLASHING you must use Path A.
POST https://verification.didit.me/v3/passive-liveness/
Content-Type: multipart/form-data
Body fields:
- image (required, file — single selfie)
- vendor_data (optional string, your user id)
Response: JSON report with liveness score, method, and warnings array.
## 3. Webhooks (Path A only — Path B returns synchronously)
- Register a webhook destination once via
POST https://verification.didit.me/v3/webhook/destinations/
Body: url, subscribed_events: ["session.verified", "session.review_started",
"session.declined"]
- Response includes secret_shared_key — store it.
- Every webhook delivery carries an X-Signature-V2 header you MUST verify
before trusting the payload. HMAC-SHA256 verification MUST run against the raw body bytes (the raw payload as Didit sent it) BEFORE any JSON parsing — re-serialising the parsed body changes whitespace and key order, which invalidates the signature.Algorithm:
1. sortKeys(payload) recursively
2. shortenFloats (truncate trailing zeros after the decimal point)
3. JSON.stringify the result
4. HMAC-SHA256 with the secret_shared_key
5. Hex-encode, compare to the X-Signature-V2 header.
## 4. Reading the report (both paths return the same shape)
The liveness object includes:
- status: "Approved" | "Declined" | "In Review" | "Not Finished"
- method: "PASSIVE" | "FLASHING" | "ACTIVE_3D"
- score: number 0-100 (normalized liveness score)
- reference_image: signed URL to the captured selfie (expires in 1 hour)
- video_url: signed URL to the capture video, present only for FLASHING
and ACTIVE_3D (expires in 1 hour)
- age_estimation: { age, age_range } when enabled in the workflow
- warnings: Array<{ risk, log_type, short_description, long_description }>
Auto-decline risks (always enforced by Didit, not configurable):
- NO_FACE_DETECTED
- LIVENESS_FACE_ATTACK
- FACE_IN_BLOCKLIST
Configurable risks (action per workflow — Decline, Review, or Approve):
- LOW_LIVENESS_SCORE
- POSSIBLE_DUPLICATED_FACE
- DUPLICATED_FACE
- MULTIPLE_FACES_DETECTED
- LOW_FACE_QUALITY
- LOW_FACE_LUMINANCE
- HIGH_FACE_LUMINANCE
## 5. Hard rules — do not change
- Base URL for /v3/* endpoints is verification.didit.me (NOT apx.didit.me).
- Feature enum is UPPERCASE: LIVENESS, ID_VERIFICATION, FACE_MATCH, AML, IP_ANALYSIS.
- Method enum is UPPERCASE: PASSIVE, FLASHING, ACTIVE_3D.
- Auth header is x-api-key (lowercase, hyphenated).
- Webhook signature header is X-Signature-V2 (NOT X-Signature).
- Always verify webhook signatures before trusting payload data.
- Status casing matches exactly: "Approved", "Declined", "In Review",
"Not Finished" (title-cased, space-separated).
## 6. Pricing reference (public)
- PASSIVE method: $0.10 per check (standalone or bundled)
- FLASHING / ACTIVE_3D methods: $0.15 per check
- Bundled in a full KYC workflow: $0.33 per session (includes Liveness)
- 500 free checks every month, forever, on every account.
## 7. Verify your integration
- Sandbox starts on signup at https://business.didit.me — no separate flag.
- Test images: deterministic synthetic faces returned in sandbox (Approved
by default; trigger Declined by sending the canonical "spoof" test image).
- Switch to live: flip the application's environment toggle in console.
When in doubt: https://docs.didit.me/core-technology/liveness/overview
Open a new country in one click. We do the hard work.
We open the local subsidiaries, secure the licenses, run the penetration tests, earn the certifications, and align with every new regulation. To ship verifications in a new country, flip a toggle. 220+ countries live, audited and pen-tested every quarter — the only identity provider an EU member-state government has formally called safer than in-person verification.
Liveness methods — passive, 3D flash, 3D action + flash.
<0s
End-to-end inference per verification.
$0.00
Per passive liveness check. 500 free every month.
Three tiers, one price list
Start free. Pay per usage. Scale to Enterprise.
500 free verifications every month, forever. Pay-as-you-go for production. Custom contracts, data residency, and SLAs (Service Level Agreements) on Enterprise.
Free
Free
$0 / month. No credit card required.
Free KYC bundle (ID Verification + Passive Liveness + Face Match + Device & IP Analysis) — 500 / month, every month
Blocklisted Users
Duplicate Detection
200+ fraud signals on every session
Reusable KYC across the Didit network
Case Management Platform
Workflow Builder
Public docs, sandbox, SDKs, MCP (Model Context Protocol) server