v2.0 Now Live — Support for HIPAA Workloads

Secure documents.
Zero manual effort.

The enterprise-grade PII detection API. Send us your messy documents, get back perfectly redacted files in milliseconds.

api.piiscrubber.com/v1/redact
Active Session
Request.py content_copy
Document Preview • Scanning
✓ Entity Detected
type: "SOCIAL_SECURITY"
score: 0.9994
<50ms
Per Page Latency
99.9%
Detection Recall
Zero
Data Retention
SOC2
Compliance Ready
Use Cases

Built for critical workflows

gavel

Law Firms

Automate discovery redaction for thousands of documents. Ensure no client PII ever leaves your secure environment.

medical_services

Healthcare

De-identify patient records for research or billing while staying fully HIPAA compliant via our stateless processing.

groups

HR & Fintech

Scrub SSNs and banking details from resumes and loan applications before they hit your internal analytics tools.

Integration

Deploy in minutes, not days.

1

Auth instantly

arrow_forward

Sign up via API or web to get your production-ready key in seconds.

2

Stream your files

arrow_forward

Send files as binary streams for maximum security and speed.

3

Receive clean data

arrow_forward

Get back redacted files or detection coordinates immediately.

Signup Endpoint

Pricing for every scale

Start for free, upgrade when you ship.

Free
$0
20 docs / month
  • check_circle All 9 PII Types
  • check_circle PDF & DOCX Support
  • check_circle Community Support
Starter
$49
500 docs / month
  • check_circle Everything in Free
  • check_circle Priority Email Support
  • check_circle API v2 Access
  • check_circle Usage Analytics
Most Popular
Pro
$199
5,000 docs / month
  • check_circle Everything in Starter
  • check_circle Custom Thresholds
  • check_circle Bulk Upload API
  • check_circle Custom Webhooks
  • check_circle Dedicated Slack Channel
Enterprise
$999+
Unlimited docs
  • check_circle Everything in Pro
  • check_circle Dedicated Instance
  • check_circle On-Prem / VPC Deploy
  • check_circle 24/7 Phone Support
  • check_circle Custom SLA

Frequently Asked Questions

No. We process all documents entirely in-memory. Once the redacted file is generated or the API response is sent, the original data is purged immediately. We are "zero-retention" by design.
We currently support PDF (native and OCR), DOCX, TXT, and common image formats (JPG, PNG). All formats go through the same rigorous PII extraction pipeline.
Our hybrid approach (Transformer NLP + Regex) achieves 98.4% recall on standard PII types. You can adjust confidence thresholds via API parameters to tune for your specific data sensitivity needs.
Yes, for Enterprise customers. We offer a Dockerized version of our engine that can run in your VPC (AWS, Azure, GCP) to ensure data never leaves your infrastructure.
Free tier is limited to 1 request per second. Paid tiers scale up to 100+ requests per second with burst capacity. High-volume users can request custom rate increases.

Ready to secure
your data?

Join 200+ teams automating their privacy compliance. Sign up in seconds.

Terminal Signup
curl -X POST https://api.piiscrubber.com/signup \
  -d "email=your@email.com"