Developer-first OCR API

Turn any PDF into the exact data you need.

Define the fields you care about, send us a PDF, and OCR Engine returns clean, structured JSON. No templates to maintain, no manual review.

  • 99.4%field accuracy
  • <3savg. response
  • 120+languages

Built for teams automating invoices, receipts, forms, contracts & reports.

Why OCR Engine

Everything you need to read documents at scale.

A single endpoint that understands layout, language and intent — so you ship faster.

You define the schema

Send the fields and types you want back. The engine extracts only those — predictable, typed JSON every time.

Layout-aware extraction

Tables, multi-column pages and scanned documents are handled natively — no brittle coordinate templates.

Fast & async

Sub-3-second responses for most documents, with webhooks and batch endpoints for high volume.

Secure by default

Encrypted in transit and at rest. Files are processed and purged — never used for training.

120+ languages

Multilingual and mixed-script documents are recognised out of the box, including handwriting.

One simple API

A single REST endpoint and an API key. Drop it into any stack in minutes — examples included.

How it works

From PDF to structured data in three steps.

1

Get your API key

Request access through the form below. We send a key you can start testing with right away.

2

Define your parameters

List the fields and types you want extracted in a single JSON object — no training required.

3

Receive clean JSON

POST your PDF and get back exactly the parameters you defined, ready to store or process.

The API

You define the parameters. We return them.

There's nothing to configure server-side. Describe the data you want in the request body and OCR Engine maps the document to your schema — returning a confidence score alongside every field.

  • Typed fields: string, number, date, array, object
  • Per-field confidence scores
  • Works with native & scanned PDFs
Explore the full docs
POST /v1/extract
# Define exactly what you want back
curl https://api.ocrengine.io/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@statement.pdf" \
  -F 'fields={
      "account_no": "string",
      "balance": "number",
      "transactions": "array"
    }'
Get started

Request your API key.

Tell us a little about what you're building and we'll get you set up with a key and onboarding details. No credit card required to start.

  • Free sandbox tier to test
  • Response within one business day
  • Direct line to our engineers

By submitting you agree to be contacted about OCR Engine. We never share your details.