Extract structured data from KYC documents — with page-level source grounding

Name, date of birth, ID number, and expiration date — extracted as typed, auditable JSON. Every value carries a source citation and confidence score, so nothing reaches verification review unchecked.

KYC verification form extracted into structured fields — applicant, tax ID, and email — with source highlights

Trusted by enterprises, governments, and teams building document workflows at scale

Used by Lufthansa, Disney, Autodesk, UBS, Dropbox, IBM
Lufthansa
Disney
Autodesk
UBS
Dropbox
IBM

USE CASES

Example KYC document workflows

GOVERNED EXTRACTION

Why not rely on LLM-only extraction for KYC documents?

LLMs can reason over an identity document — but KYC and onboarding workflows need deterministic, auditable output grounded in the source file, not generated answers that vary between runs.

Output shape

LLM-only prompting

Generated answers that can change between runs — including plausible-looking ID numbers that don’t match the document.

Nutrient Data Extraction API

Predictable structured output — typed and tied to the source identity document.

Routing signal

LLM-only prompting

No signal for which values to trust.

Nutrient Data Extraction API

Confidence signals route uncertain fields to human review before onboarding decisions or AML screening.

Traceability

LLM-only prompting

No way to point back at the document.

Nutrient Data Extraction API

Coordinates and page references anchor every extracted field to its source location on the identity document.

Document variation

LLM-only prompting

Different issuing countries and ID formats break prompt-based extraction.

Nutrient Data Extraction API

Layout-flexible pipeline handles ID cards, passports, and driver’s licenses across issuers without per-format configuration.

Review step

LLM-only prompting

Values reach verification systems unchecked.

Nutrient Data Extraction API

Human review and validation before onboarding decisions, AML screening, or identity verification platforms.

Audit

LLM-only prompting

Nothing to show a compliance auditor.

Nutrient Data Extraction API

Source context and page detail support traceable, audit-ready KYC and identity verification workflows.

Try it live

See the parse API in action — no signup required

Switch processing modes and inspect live output from a sample identity document as rendered Markdown, raw Markdown, or spatial JSON.

HOW IT WORKS

From identity document to structured output

Parse

Turn identity document PDFs, scans, images, and phone photos into document structure.

Extract

Identify key-value regions, MRZ zones, barcodes, and form fields from ID cards, passports, and driver’s licenses.

Map

Define the fields needed using the schema generator in Studio, or write a JSON Schema directly. Get back validated, typed output.

Structure

Return typed JSON for verification systems and validation, or Markdown for search and AI workflows.

Process

Send structured data into identity verification platforms, KYB workflows, or onboarding systems.

OUTPUT FORMATS

Spatial JSON. Or Markdown. From the same API.

Confidence scores, coordinates, and page context included.
Choose output: "json" or Markdown per request.

Spatial JSON

For extraction · validation · review

.json
{
"type": "keyValueRegion",
"id": "kv_m4n5o6",
"bounds": { "x": 60, "y": 90, "width": 300, "height": 128 },
"confidence": 0.97,
"page": { "pageIndex": 0, "pageNumber": 1 },
"pairs": [
{
"key": { "entityType": "QUESTION", "value": "Full name", "bounds": { "x": 60, "y": 90, "width": 100, "height": 24 }, "confidence": 0.99 },
"value": { "entityType": "ANSWER", "value": "Jordan Ellis", "bounds": { "x": 168, "y": 90, "width": 120, "height": 24 }, "confidence": 0.99 },
"relationshipConfidence": 0.97
},
{
"key": { "entityType": "QUESTION", "value": "Date of birth", "bounds": { "x": 60, "y": 126, "width": 100, "height": 24 }, "confidence": 0.98 },
"value": { "entityType": "ANSWER", "value": "1990-07-14", "bounds": { "x": 168, "y": 126, "width": 100, "height": 24 }, "confidence": 0.98 },
"relationshipConfidence": 0.96
},
{
"key": { "entityType": "QUESTION", "value": "Document number", "bounds": { "x": 60, "y": 162, "width": 100, "height": 24 }, "confidence": 0.98 },
"value": { "entityType": "ANSWER", "value": "X1234567", "bounds": { "x": 168, "y": 162, "width": 100, "height": 24 }, "confidence": 0.98 },
"relationshipConfidence": 0.96
}
]
}

Markdown

For RAG · search · knowledge bases

.md
# Identity Document
**Full name** Jordan Ellis
**Date of birth** 1990-07-14
**Document number** X1234567
**Expiration date** 2029-07-14

ACCURACY

Benchmarked accuracy, KYC-specific numbers in progress

Accuracy benchmarks specific to identity documents aren’t published yet. In the meantime, the general Data Extraction API benchmark — reading order, table structure, and heading hierarchy, tested on a 200-document corpus with every release — is the current accuracy proof.

0.94
Table structure accuracy (TEDS), OpenDataLoader benchmark, understand mode
KYC-specific benchmark numbers aren’t published yet. The closest available proxy is key-value region extraction accuracy on the general benchmark. View accuracy benchmarks →

Regional processing options

Choose supported processing regions for enterprise deployments.

SOC 2 Type 2 audited

Audited annually. Reports available under NDA for enterprise customers.

Trust and compliance

Built for identity verification workflows in production

TLS encryption by default

All API communication is encrypted. Unencrypted requests are rejected.

Configurable data retention

Encrypted transport and plan-level retention controls for identity document workflows.

KYC document extraction questions

Can the API extract fields from ID cards and passports?

Yes. The extract endpoint maps identity documents to a JSON Schema you define, so name, date of birth, document number, and expiration date can be extracted consistently across document types and issuing countries.

Is this a KYC or identity-verification platform?

No. Nutrient Data Extraction API is an extraction layer, not an identity-verification or KYC platform. It turns identity documents into structured data so that data can be reviewed and routed into the verification or onboarding system your team already uses.

How do I validate extracted identity data before onboarding?

Every extracted field includes a match label, confidence score, page reference, and bounding box, so uncertain fields can be flagged for human review and traced back to the source document before an onboarding decision.

What file formats are supported?

Data Extraction API processes images (including phone photos of ID documents), PDFs, and scans, without requiring a separate OCR pipeline.

GET STARTED

Start extracting data from KYC documents

5,000 free credits per month — no credit card required.

Your free account includes:

    • 5,000 Data Extraction API credits per month
    • Parse PDFs, scans, images, and Office files
    • Typed JSON output with confidence scores and source context
    • SOC 2 Type 2 audited