dOCR
Getting Started

Overview

What dOCR does and when to use it.

dOCR is a document data-extraction API. You send a document; dOCR returns structured JSON.

When to use dOCR

  • You receive documents (invoices, receipts, statements, forms, IDs) and need the data in a database or workflow.
  • You want structured fields, not raw OCR text.
  • You'd rather call one API than build and maintain OCR + parsing + LLM pipelines yourself.

Two ways to use it

  1. Dashboard — upload documents in the web app and view results in Extraction History. Good for ad-hoc extractions and trying things out.
  2. API — call POST /api/v1/extract from your backend to automate extraction at scale. This documentation focuses on the API.

Next steps

Quickstart

Run your first extraction with curl.

Core concepts

Documents, document types, extractions, and pages.

Introduction

dOCR turns documents into structured data and renders web pages into images — one API, one set of credits.

Quickstart

Make your first extraction in under five minutes.

On this page

When to use dOCRTwo ways to use itNext steps