Hanji is a document parsing and extraction API that converts complex documents such as medical insurance forms, government paperwork, and scanned faxes into structured, AI-ready data. It targets developers and operations teams in healthcare, insurance, and government sectors, including enterprises with high-volume needs. The service offers a grounded extraction pipeline where every value is cited back to its source, with automatic re-reading of failed pages and flagging of unverifiable fields. It is delivered as a cloud API with a free tier and enterprise options, including HIPAA compliance and uptime SLAs.
Key features
- Parse any document into grounded structure
- Extract fields with cited sources
- Automatic re-read of failed pages
- Flag unverifiable values for review
- Bounding boxes on every element
- Schema-based extraction with null for ungrounded
- Tune on edge cases for accuracy
- HIPAA compliance with BAA
- SOC 2 Type II in progress
- Rate limiting and secret scanning
Social posts
- No social media activity within the last 30 days
GTM channels
- API
- Docs
ICP
- Software developers
- Engineering teams
- Enterprises