KYC and Customer Onboarding
Automate customer registration by extracting identity data from passports, national ID cards and driver licenses.
ID scanning as a service.
API-first. Privacy-first. Multi-country.
Submit identity document images via REST API and get structured, merged field data back - no app to install, no SDK to embed.
Session-based async processing with real-time partial results
Multi-image fusion extracts more from front + back combined
No ID images stored. No exceptions.
Built for businesses and apps that need reliable, privacy-first identity document verification.
Identity document OCR API
Identity Document OCR API for Modern Applications
IdScanly provides an AI-powered identity document OCR API that extracts structured information from passports, identity cards, residence permits, visas and driver licenses.
Whether you are building a KYC platform, fintech onboarding workflow, access control system, customer registration process or compliance solution, IdScanly helps automate document data extraction through a simple REST API.
The platform combines OCR, MRZ recognition, barcode reading and multi-image analysis to maximize accuracy while maintaining a privacy-first architecture.
Common use cases
Common Identity Verification Use Cases
Fintech and Banking
Accelerate Know Your Customer (KYC) procedures and reduce manual data entry during account creation.
Travel and Hospitality
Capture guest information from passports and identity cards during hotel check-in processes.
Access Control and Security
Verify visitor identities and automate registration workflows using machine-readable identity documents.
Car Rental and Mobility Services
Extract and validate driver license information during vehicle rental and onboarding processes.
- Document signal
- MRZ
- Validation
- Checksums
- Merged with
- OCR + barcode
MRZ recognition and passport OCR
MRZ Recognition API
Machine Readable Zone (MRZ) recognition allows software systems to extract highly reliable identity information directly from passports and many government-issued identity cards.
IdScanly automatically detects MRZ zones, validates checksum digits and merges MRZ information with OCR and barcode results to increase extraction accuracy.
The MRZ scanner API is suitable for passport verification, border control systems, travel applications and digital identity onboarding workflows.
Privacy-first verification
Privacy-First Identity Verification API
Many document scanning solutions store sensitive identity documents indefinitely. IdScanly was designed differently.
Identity document images are processed in memory and discarded after processing by default. No document archives, galleries or long-term image storage are required.
This architecture helps organizations reduce compliance risks while maintaining control over personal information.
- No long-term identity document image storage by default
- No document galleries or archives required
- Designed to reduce privacy and compliance exposure
Why this is different
Parallel OCR layers
Multiple independent recognition engines run concurrently - text, color, MRZ, barcode, and visual zones process in parallel so results arrive fast.
Zero storage by default
Images are processed and discarded. No document gallery, no retention by default. Configure your own retention policy if needed.
Session-based fusion
Upload front and back into one session. The engine continuously merges candidates and selects the strongest value per field across all images.
Confidence scores + source traces
Every extracted field includes:
- Confidence score (0–1)
- Source layer (MRZ, OCR, barcode)
- Originating image ID
- Alternative candidates
Multi-country support
Designed for multiple document formats and countries. Unknown document types still return partial fields and raw OCR data.
Built for your backend
API Integration
Call the REST API from your own backend. Submit images, poll for results, read structured fields.
- Session-based workflow: create → upload → poll
- Partial results available before processing completes
- JPEG, PNG, WebP, HEIC/HEIF supported
Best for:
Backend teams, fintechs, KYC platforms, onboarding flows, access control systems
Self-hosted / Enterprise
Run IdScanly on your own infrastructure for maximum data sovereignty and custom SLAs.
- Deploy on your own servers or private cloud
- Full control over data retention and encryption
- Custom rate limits, audit logs, and monitoring
Best for:
Regulated industries, government, large enterprises, privacy-critical deployments
What it extracts
Structured field extraction designed for compliance and downstream processing.
- Name, document number, date of birth, expiry date, nationality
- Document type + issuing country, MRZ data with checksum validation
- All fields returned as JSON with confidence scores and source traces
Supported fields vary by document type. Unknown documents still return partial data.
Security & privacy
Privacy is a design constraint, not a checkbox.
Server-side processing
No image retention
No document databases
No plaintext logging
Designed for compliance
API responses carry Cache-Control: no-store. Images are processed and not retained by default. Request IDs are logged - not document content.
Enterprise controls:
- Configurable retention periods and encryption keys
- Network allowlisting / IP restrictions
- Audit-friendly logs (request IDs and metadata only)
How it works
Simple, three-step integration
1
Create a session
One API call initializes a scan session and returns a session identifier you use for uploads and polling.
2
Upload document images
Submit the front and back of the document as separate images in the same session. Multiple OCR engines process them in parallel.
3
Poll and read results
Poll the session endpoint every couple of seconds until processing completes.
- •Partial fields appear as recognition layers finish
- •Final result includes merged fields with confidence scores
Pricing
Choose the plan that fits your integration
Pay as you go
For prototypes and variable usage.
Simple usage-based pricing per scan session with transparent volume tiers.
POPULAR
Monthly subscription
Predictable costs for production workloads.
Includes a monthly session allowance + discounted overage rate.
Enterprise
Custom pricing for high volume, self-hosted deployments, and SLAs.
Includes dedicated infrastructure, custom rate limits, and integration support.
Frequently Asked Questions
Do you store ID images?
No. Images are processed server-side and discarded. No document gallery or retention by default. Enterprise deployments can configure custom retention with encryption.
How do I authenticate?
Send your API key in the x-api-key request header. Keys are provisioned by IdScanly - contact support to request one. Never embed keys in client-side code.
Which countries and document types are supported?
Multi-country support is a core goal. The engine processes unknown document types and still returns partial fields, MRZ data, and raw OCR output. We continuously expand coverage.
Can I upload front and back of the same document?
Yes - this is recommended. Upload both into the same session. The engine fuses field candidates from all images and selects the strongest value per field.
When is the result ready?
Poll the session endpoint every couple of seconds. Once processing is complete, you receive the merged result with field values and confidence scores. Partial fields are available as individual recognition layers finish.
Coming soon
Features actively in development
PDF417 barcode support (US/Canada driver licenses)
Webhook notifications on session completion
Admin dashboard with usage metrics and error rates
Field validation rules (expiry checks, required fields)
Quality score endpoint before full processing
Batch session creation
Country rollout page with coverage details
Fraud-resistance signals in result metadata
Ready to integrate?
Get API access and start extracting structured data from identity documents today.