Skip to content

Face Match Verification API

Popular

Compare a captured face image with a reference photo from an identity document or an existing customer record. Use the result in your own onboarding, re-verification or fraud review.

Overview

Face match compares two face images and returns a structured similarity result your application can act on. One image is captured during the check. The other is one the business already trusts, such as the photograph on a submitted identity document or a photo held in an existing customer record. Read the result as a signal, not a verdict. Teams usually read it alongside document verification and the other checks in the same journey. Strong comparisons move forward, borderline ones go to a reviewer, and an unusable image is captured again. Face match confirms that two images show the same person. It does not confirm that the capture came from a live person at the camera, which is what the separate Face Liveness service checks. Most identity journeys run the two together, with consent recorded for both. The fields available in a response can vary by data source and record.

Category
KYC Services
Coverage
India-wide onboarding and re-verification journeys. Supported image sources depend on your service contract.
Input
A captured face image and a reference face image
Output
Structured similarity and image-quality information, where available
Typical users
Lending, insurance, fintech, marketplaces, logistics, staffing and telecom teams
Coverage note
Fields available vary by data source and record, and by your service contract

The overview and the sections after the reference are the FinSour API catalog’s own record for this service, rendered unaltered.

Endpoint URL and method

POSThttps://gateway.staging.finsour.io/v1/identity/face-match

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Authentication

Scheme API key travels in the X-Api-Key header

Send your API key in this header on every call, from your own server: a key sent from a browser is refused. A key starting fs_test_ calls the sandbox and one starting fs_live_ calls production, at the same address. Create keys in the FinSour console.

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Request parameters

Content type application/json

Headers

NameTypeRequiredDescriptionConstraints
Idempotency-KeystringRequiredA key you generate for each attempt. Sending the same key again returns the first answer instead of running the check twice; the same key with a different body is refused.8 to 255 characters. Matches ^[A-Za-z0-9._:-]+$

Body

NameTypeRequiredDescriptionConstraints
inputobjectRequiredThe details to check.—
input.idImagestringRequiredThe photograph on the identity document: base64 of a JPEG or PNG, no data: prefix.Matches ^[A-Za-z0-9+/]+={0,2}$. 100 to 460000 characters
input.selfieImagestringRequiredA photograph of the person presenting it: base64 of a JPEG or PNG, no data: prefix.Matches ^[A-Za-z0-9+/]+={0,2}$. 100 to 460000 characters
optionsobjectRequiredSettings for this call. This API requires consent.—
options.referencestringOptionalYour own reference for this call. It comes back unchanged as meta.reference.1 to 128 characters
options.consentobjectRequiredThe person's consent to this check.—
options.consent.obtainedbooleanRequiredSend true once the person has agreed to the check.Always true
options.consent.atstring (date-time)RequiredWhen the person gave consent.—
options.consent.purposestringRequiredWhat the check is for, for example kyc.1 to 64 characters

Request samples

cURL

curl -X POST https://gateway.staging.finsour.io/v1/identity/face-match \
  -H "X-Api-Key: $FINSOUR_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "idImage": "<idImage>",
    "selfieImage": "<selfieImage>"
  },
  "options": {
    "consent": {
      "obtained": "<obtained>",
      "at": "<at>",
      "purpose": "<purpose>"
    }
  }
}'

Node.js

const response = await fetch("https://gateway.staging.finsour.io/v1/identity/face-match", {
  method: "POST",
  headers: {
    "X-Api-Key": process.env.FINSOUR_API_KEY,
    "Idempotency-Key": crypto.randomUUID(),
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "input": {
      "idImage": "<idImage>",
      "selfieImage": "<selfieImage>"
    },
    "options": {
      "consent": {
        "obtained": "<obtained>",
        "at": "<at>",
        "purpose": "<purpose>"
      }
    }
  }),
});

console.log(response.status, await response.json());

Python

import os
import uuid

import requests

response = requests.post(
    "https://gateway.staging.finsour.io/v1/identity/face-match",
    headers={
        "X-Api-Key": os.environ["FINSOUR_API_KEY"],
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "input": {
            "idImage": "<idImage>",
            "selfieImage": "<selfieImage>",
        },
        "options": {
            "consent": {
                "obtained": "<obtained>",
                "at": "<at>",
                "purpose": "<purpose>",
            },
        },
    },
    timeout=30,
)

print(response.status_code, response.json())

Generated from the fields above. Replace each value in angle brackets with your own; the key is read from FINSOUR_API_KEY.

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Response schema

Status 200 · content type application/json

NameTypePresentDescriptionConstraints
dataobjectAlwaysThe result of the check.—
data.foundbooleanAlways——
data.matchScorenumber or nullAlwaysHow alike the two faces are, 0 (not at all) to 100 (the same face), to two decimals.Minimum 0. Maximum 100
data.sourceobjectAlways——
data.source.fetchedAtstringAlwaysWhen the answer was fetched: RFC 3339 UTC with a Z, never an epoch or an IST offset.Matches ^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d{1,9})?Z$

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Error codes

CodeStatusMeaningRetrying
API_VERSION_UNSUPPORTED400That API version is no longer supported.Do not retry automatically
IDEMPOTENCY_KEY_INVALID400That Idempotency-Key does not meet the required format.Do not retry automatically
IDEMPOTENCY_KEY_REQUIRED400An Idempotency-Key header is required for this request.Do not retry automatically
REQUEST_MALFORMED400The request could not be parsed.Do not retry automatically
AUTH_KEY_EXPIRED401The API key is not valid.Do not retry automatically
AUTH_KEY_INVALID401The API key is not valid.Do not retry automatically
AUTH_KEY_MISSING401No API key was presented.Do not retry automatically
AUTH_KEY_REVOKED401The API key is not valid.Do not retry automatically
INSUFFICIENT_BALANCE402The available balance is not enough for this request.Do not retry automatically
AUTH_IP_NOT_ALLOWED403This API key may not be used from this address.Do not retry automatically
ENTITLEMENT_MISSING403This organization is not entitled to that product in this environment.Do not retry automatically
ORGANIZATION_SUSPENDED403This organization is not active.Do not retry automatically
PRODUCT_NOT_AVAILABLE403That product is not available.Do not retry automatically
PRODUCT_RETIRED403That product has been withdrawn.Do not retry automatically
SCOPE_INSUFFICIENT403This API key does not carry the scope this product requires.Do not retry automatically
PRODUCT_NOT_FOUND404No such product.Do not retry automatically
IDEMPOTENCY_KEY_REUSED409That idempotency key was already used for a different request.Do not retry automatically
PRICE_UNAVAILABLE409No active price covers this product right now.Safe to retry
REQUEST_IN_PROGRESS409An earlier attempt with this key is still running.Safe to retry
SETTLEMENT_PENDING409This request is awaiting reconciliation by an operator.Do not retry automatically
API_VERSION_SUNSET410That API version passed its announced sunset date.Do not retry automatically
REQUEST_TOO_LARGE413The request body is too large.Do not retry automatically
UNSUPPORTED_MEDIA_TYPE415That content type is not accepted on this route.Do not retry automatically
CONSENT_REQUIRED422This product requires an explicit consent flag.Do not retry automatically
SANDBOX_FIXTURE_MISSING422No sandbox fixture exists for this input. Use a different test value.Do not retry automatically
UPSTREAM_REJECTED422The upstream source rejected the input.Do not retry automatically
VALIDATION_FAILED422The request payload is invalid.Do not retry automatically
CONCURRENCY_LIMIT429Too many simultaneous requests.Safe to retry
QUOTA_EXCEEDED429The allowance for this window is spent.Do not retry automatically
RATE_LIMITED429Too many requests.Safe to retry
INTERNAL_ERROR500An unexpected error occurred.Safe to retry
OUTCOME_UNCERTAIN502The outcome of this request is not yet known. Retry with the same Idempotency-Key.Do not retry automatically
UPSTREAM_UNAVAILABLE502The upstream source is unavailable. Retry shortly.Safe to retry
MAINTENANCE_MODE503The service is in a maintenance window.Safe to retry
NO_PROVIDER_AVAILABLE503No provider can serve this product right now.Safe to retry
SERVICE_OVERLOADED503The service is shedding load. Retry shortly.Safe to retry
UPSTREAM_TIMEOUT504The upstream source did not respond in time.Safe to retry

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Rate limits

ScopeLimitWindowAt the limit
Your API key, within your organisation's limitThe figure in X-RateLimit-LimitPer minute429 RATE_LIMITED, with Retry-After in seconds. Every answer past authentication carries X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.

Supplied by FinSour platform API contract (finsour development at 80e8b83bf) on . OpenAPI document at commit 436311c32, API version 2026-11-01. The beta is served from the staging gateway.

Use cases

  • Banks, lending and NBFCs: match the applicant selfie to the ID photo before disbursal
  • Insurance: check a claimant against the policyholder record before a claim moves
  • Fintech and payment providers: step-up checks on device changes and account recovery
  • Logistics and fleet: confirm the driver starting a shift matches the license on file
  • Staffing and gig platforms: shift-start checks that deter account renting and sharing
  • Telecom and retail networks: verify distributors and store staff at the point of sale

What this service does

  • A comparison result you can route on

    Send a captured image and a reference image and receive a structured similarity result, together with the image-quality signals the service returns. The fields available vary by data source and record, and by your service contract.

  • Runs alongside a liveness check

    Face match can confirm that two images show the same person. It cannot confirm that the capture was a live person. Running it after the separate Face Liveness service narrows the gap that a printed photo or a screen replay would otherwise leave open.

  • The same comparison on every file

    Manual photo comparison depends on who is reviewing and how long the queue is. An API applies one comparison to every case. Onboarding at volume does not drift with the reviewer or the hour.

  • Built for a consented journey

    A face image is personal data. The check is designed for journeys where the person has been told what the image will be compared against and has agreed to it. Use of the result stays inside the purpose you declared.

How a check runs

  1. Capture the face image with consent

    Take the capture inside a guided step in your app or web journey. Run it after the person has been told what the image will be compared against, and has agreed to it.

  2. Pick the reference photo

    Supply the photo you already trust: the image read from a submitted identity document, an enrollment photo, or one held in the customer record.

  3. Send both images for comparison

    Your application submits the pair through the API as part of the onboarding, re-verification or review step it already runs.

  4. Read the similarity and quality signals

    The response returns the available similarity and image-quality information as structured fields. Which fields you get depends on the data source and the record.

  5. Apply your own thresholds

    Proceed, send the case to a reviewer, or request a fresh capture. Keep the decision and the reason for it in your audit trail.

Questions

What is a face match API?
An interface that compares two face images inside your own software. Your application sends a captured image and a reference image, and receives a structured similarity result. You can use it in an onboarding, re-verification or review workflow, instead of asking a person to compare the photos by hand.
What is the difference between face match and face liveness?
Face match compares two images to judge whether they show the same person. Face Liveness, a separate service, examines whether a capture came from a live person at the camera, not a printed photo, a screen or a stored file. Journeys commonly run liveness first, then face match to tie the capture to the document.
What can I use as the reference image?
Any face photo your business already trusts and is authorized to use for that purpose. That can be the photograph on a submitted identity document, a photo captured when the person first enrolled, or one held in the existing customer record. Reference photos taken from documents can be small, textured or older than the person at the camera, and that affects how strong a comparison the service can return.
Does a face match result prove who someone is?
No, the result is a similarity signal about two images. Read it alongside document verification and the other checks in the same journey. Your own thresholds decide what proceeds, what goes to a reviewer and what needs a fresh capture.
Do I need consent to run a face match?
Tell the person what the image is for and get their agreement before it is captured, since a face image is personal data about an identifiable person. Record that consent with the case, and honor a withdrawal. Use the comparison only for the purpose you collected it for, and keep the images no longer than that purpose needs.
Can I use face match to re-verify an existing customer?
Yes, where the earlier image was collected for a purpose that covers it and the person has agreed. Common examples are a step-up check when an account is reached from a new device. Others are a re-check before payout details change, and periodic reviews on long-running policies or entitlements.

Catalog entry last updated .