Skip to content
Beta · IDP API

Read any document.
Get structured JSON.
In 50+ languages.

eScanX is an Intelligent Document Processing (IDP) API - beyond basic OCR. It classifies and extracts structured data from invoices, receipts, purchase orders, bank statements, and more, in any format, returning clean JSON for any system.

Example response (beta)
POST /api/v1/process

{
  "document_type": "invoice",
  "language": "de",
  "confidence": 0.94,
  "fields": {
    "vendor": "Acme GmbH",
    "invoice_number": "INV-2026-0142",
    "currency": "EUR",
    "tax": 250.00,
    "total": 1250.00
  },
  "line_items": [ ... ],
  "review_required": false
}

How eScanX works

01

Upload

Send any document - invoice, receipt, PO, bank statement - as an image or PDF, in any format.

02

Classify & Extract

eScanX identifies the document type, then extracts every field with a confidence score per section.

03

Get JSON

Receive clean, structured JSON for any system. Anything below your threshold is flagged for review.

Documents

What eScanX Handles

One API for structured and unstructured documents - including, but not limited to, the formats below.

Invoices

Vendor, line items, tax, totals

Receipts

Merchant, items, amounts, dates

Purchase Orders

PO number, supplier, quantities

Sales Orders

Customer, SKUs, pricing, terms

Bank Statements

Transactions, balances, periods

Any Format

PDF, image, or scan - structured or not

Why eScanX

Designed for Production, Built for Privacy

Classify, Then Extract

Goes beyond OCR. eScanX identifies the document type first, then pulls structured data - no per-template setup to maintain for supported document types.

Confidence Per Section

Every section returns a confidence score. Set your own auto-approve threshold; anything below it is flagged for human review.

50+ Languages

Process documents in over 50 languages through one API, with no per-language setup on your side.

EU-Hosted & GDPR-Native

Hosted in the EU and built for GDPR from the ground up - not bolted on after the fact.

No Third-Party AI

No external AI APIs in the background. Your documents are processed only on our own EU-hosted infrastructure - never sent to outside AI providers.

Zero Retention

We do not keep your documents. They are deleted after processing on a schedule you control.

Use Cases

Where eScanX Fits Best

High-Volume Processing

Automate document-heavy operations - accounts payable, claims, onboarding - where manual data entry can no longer keep up.

Multi-Format & Multi-Language

Handle mixed document types across 50+ languages through a single API, with no per-format or per-language setup.

Embed Extraction in Your Product

Add document understanding to your own app or platform with one API call. We handle the AI; you ship the feature.

Workflow Automation

Pair eScanX with n8n or Make to build end-to-end pipelines - from document to your system of record.

Dashboard

Manage everything from one dashboard

Track usage and credits, monitor extraction health, manage your API keys, and switch plans - all from a single console.

app.escanx.com
The eScanX dashboard showing credits remaining, documents processed, extraction health, current plan, and API keys.

Roadmap

What's Coming Next

IDP API - classify and extract structured data as JSON

In beta

Confidence scoring with customer-set review thresholds

In beta

50+ language document support

In beta

Multi-format support - PDF, JPG, PNG, TIFF

In beta

Direct integrations - Xero, QuickBooks, SAP

Soon

Bulk processing - batch upload via API

Soon

Dashboard & analytics portal

Planned

Webhooks for real-time processing updates

Planned

FAQ

Frequently asked questions

How is eScanX different from regular OCR?

OCR just turns an image into raw text. eScanX is Intelligent Document Processing: it first classifies the document type, then extracts the specific fields that matter and returns them as structured JSON - with a confidence score per section.

Which documents and languages does it support?

Invoices, receipts, purchase orders, sales orders, bank statements, and more, in over 50 languages through a single API - structured or unstructured.

Where are my documents processed and stored?

Everything is hosted in the EU and built GDPR-native. Documents are not sent to any third-party AI provider and are not retained - they are deleted after processing on a schedule you control.

Is eScanX production-ready?

eScanX is currently in beta. You can request early API access now and start turning documents into structured data while it matures.

How do I get started?

Read the API docs at escanx.com/docs to see the endpoints and response format, or request beta access through our contact form and we will get you set up.

eScanX is in beta.

Get early API access and start turning your documents into structured data.

Request Beta Access

Prefer to dig in first? Read the API docs.

Built by Erichsol - QA & automation experts from Finland.