Protect confidential data and save valuable time by seamlessly automating PDF redaction with AI-powered accuracy and efficiency.
Automatically detects and redacts PII like names, locations, emails, and dates.
Leverages advanced AI to understand context and make precise redactions.
Ideal for batch processing — redact hundreds of documents programmatically.
Common languages support: English, Spanish, German, Italian, Russian, etc.
Including rotated or vertical text.
Includes signatures, QR codes, and faces.
HTTPS-only transport; we retain zero data after processing.
Use JSON (base64) or multipart/form-data.
Need control? Run our API on your infrastructure with full data governance.
per month
Redact the first 10 pages
5 requests/minute — for testing & prototyping
OCR: image based PDF files supported
English language support
Try For Freeper page
Scalable for business needs
On-premise deployment
OCR: image based PDF files supported
Common languages support
Contact UsThese are the types of personally identifiable information (PII) we detect in your data:
Read the docs and explore our playground.
View DocumentationDeploy on your own infrastructure with Docker. Keep full control over your data and compliance.
No data leaves your servers. Perfect for regulated industries requiring on-premise solutions.
Process documents without internet connectivity. Ideal for air-gapped or secure environments.
One-command installation with Docker Compose. Professional setup with persistent volumes.
Built-in OCR supporting 7 languages: English, Spanish, French, German, Italian, Portuguese, Russian.
Customize processing limits, LLM integration, and server settings via environment variables.
Try the self-hosted API risk-free with a full 14-day trial period to evaluate its capabilities.
Explore our example notebooks demonstrating how to integrate with the PDF Redaction REST API.
View on GitHubAccess documentation, request a trial API key, or schedule an architectural planning session with our team.
The PDF Redaction API is a RESTful service that allows you to automatically detect and redact sensitive information from PDF documents using AI-powered analysis.
Sign up for an API key, review the documentation, and start making requests to the endpoints. We offer a free tier for testing and prototyping.
The API can detect emails, credit card numbers, tax IDs, phone numbers, names, addresses, dates, and other sensitive information automatically.
Yes, the API uses HTTPS encryption and does not store your documents. Processing is done in memory and data is discarded immediately after processing.
Yes, we offer a self-hosted Docker version of the API for complete data control and on-premise deployment.
Yes, the API supports multi-page PDFs. Processing limits can be configured, with default maximums of 10 pages for PII detection and redaction.
The API includes built-in OCR support for 7 languages: English, Spanish, French, German, Italian, Portuguese, and Russian. Additional languages can be supported through custom configurations.
Yes, the API can detect and redact various image-based elements including signatures, QR codes, faces, and other visual PII in PDF documents.
Yes, the API can detect and redact PII in text with any orientation, including rotated and vertical text within PDF documents.
