Home › Directory › OCR & Document Parsing
OCR & Document Parsing
OCR engines and document parsers that turn PDFs, scans and Office files into structured text.
JSON: /api/v1/directory.json (filter on category=ocr-document-parsing)
Firecrawl
Turns websites into clean markdown or structured data, with crawl, scrape and map endpoints.
Free tierAPI keyTesseract OCR
The classic open-source OCR engine supporting 100+ languages.
FreeNo authPaddleOCR
Open-source multilingual OCR and document parsing toolkit.
FreeNo authEasyOCR
Ready-to-use Python OCR library for 80+ languages.
FreeNo authdocTR
Document text recognition library for TensorFlow and PyTorch.
FreeNo authSurya
OCR, layout analysis and reading-order models for 90+ languages.
FreeNo authMarker
Converts PDFs, images and Office files to markdown and JSON quickly and accurately.
FreeNo authDocling
IBM-originated open-source toolkit that parses PDFs and documents into structured formats for GenAI.
FreeNo authUnstructured
Open-source and hosted ETL for turning documents into LLM-ready structured data.
Free tierAPI keyLlamaParse
LlamaIndex's genAI-native document parsing API.
Free tierAPI keyMistral OCR
Mistral's OCR API for extracting text, tables and images from documents.
PaidAPI keyGoogle Document AI
Google Cloud service for extracting structured data from documents.
PaidOAuthAWS Textract
AWS service that extracts text, forms and tables from scanned documents.
PaidOAuthAzure AI Document Intelligence
Microsoft's service for extracting text, key-value pairs and tables from documents.
Free tierAPI keyMathpix
OCR API specialized in math, science and handwritten content.
PaidAPI keyOCR.space
Free OCR API with a generous free tier for images and PDFs.
Free tierAPI keyNanonets
Document AI and OCR for invoices, receipts and custom documents.
PaidAPI keyMindee
APIs for parsing invoices, receipts, IDs and custom documents.
Free tierAPI keyReducto
Document ingestion API for accurate parsing of complex PDFs for LLMs.
PaidAPI keyAzure Content Understanding
Microsoft service to convert multimodal content into structured output.
PaidAPI keyPyMuPDF
Python library for fast PDF and document text, image and metadata extraction.
FreeNo authpdfplumber
Python library to extract text and tables from PDFs.
FreeNo authApache Tika
Detects and extracts text and metadata from over a thousand file types.
FreeNo authMarkItDown
Microsoft's tool to convert files and Office documents to Markdown for LLMs.
FreeNo authpdf.js
Mozilla's JavaScript library for parsing and rendering PDFs.
FreeNo autholmOCR
Allen AI's toolkit for converting PDFs into clean text with vision language models.
FreeNo authPDF.co
Web API for PDF parsing, conversion, merging and generation.
Free tierAPI keyStirling-PDF
Self-hosted web app and API for PDF manipulation.
FreeNo authGotenberg
Docker-based API for converting documents and web pages to PDF.
FreeNo auth