LeapOCR Documentation

Transform documents into structured data using AI-powered OCR. Complete API reference, SDK guides, and examples for JavaScript, Python, and Go.

LeapOCR provides enterprise-grade document processing with AI-powered data extraction. Transform PDFs and images into structured data, markdown, or custom formats using our powerful API and SDKs.

Get Started in 5 Minutes

Getting Started

Complete walkthrough to process your first document

Choose Your SDK

Pick from JavaScript, Python, Go, or REST API

API Reference

Complete REST API documentation

Use Cases

Real-world examples and patterns

Key Features

AI-Powered Extraction - Advanced OCR with multiple model options
Multiple Output Formats - Structured JSON, markdown, or per-page processing
Custom Schemas - Define your own extraction schemas with JSON Schema
Custom Instructions - Define your own extraction instructions to guide the model
Custom Templates - Define your own document templates with predefined schemas, instructions settings

Quick Start

Choose your language to get started:

import { LeapOCR } from "leapocr";

const client = new LeapOCR({ apiKey: process.env.LEAPOCR_API_KEY });

const job = await client.ocr.processURL("https://example.com/invoice.pdf", {
  format: "structured",
  instructions: "Extract invoice number, date, and total",
});

const result = await client.ocr.waitUntilDone(job.jobId);

View full JavaScript guide →

from leapocr import LeapOCR, ProcessOptions, Format

async with LeapOCR(os.getenv("LEAPOCR_API_KEY")) as client:
    result = await client.ocr.process_and_wait(
        "https://example.com/invoice.pdf",
        options=ProcessOptions(
            format=Format.STRUCTURED,
            instructions="Extract invoice number, date, and total"
        )
    )

View full Python guide →

client, _ := ocr.New(os.Getenv("LEAPOCR_API_KEY"))

job, _ := client.ProcessURL(ctx, "https://example.com/invoice.pdf",
    ocr.WithFormat(ocr.FormatStructured),
    ocr.WithInstructions("Extract invoice number, date, and total"),
)

result, _ := client.WaitUntilDone(ctx, job.ID)

View full Go guide →

# Submit document from URL
curl -X POST https://api.leapocr.com/ocr/uploads/url \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/invoice.pdf",
    "format": "structured",
    "instructions": "Extract invoice number, date, and total"
  }'

# Get result
curl https://api.leapocr.com/ocr/result/{job_id} \
  -H "X-API-Key: your-api-key"

View full API reference →

Processing Models

LeapOCR provides three AI models for document processing:

Model	Display Name	Description	Credits/Page
`standard-v1`	Standard v1	Baseline model, handles all cases	1
`english-pro-v1`	English Pro v1	Premium quality, English documents only	2
`pro-v1`	Pro v1	Highest quality, handles all cases	3