# Suparse

> AI-powered document processing platform that turns PDFs, images, and emails into structured data with human review and API access.

Suparse is an AI document processing platform that converts PDFs, images, email bodies, and attachments into structured data. Users pick a document type or use Autopilot, review low-confidence fields, and export to Excel, Google Sheets, CSV, or JSON, or send results through API and webhooks.

## What It Is

Suparse is a document data extraction service for business documents such as invoices, receipts, bank statements, purchase orders, bills of lading, and air waybills. It uses pre-trained models for common document types and an AI-assisted schema generator that creates custom parsers from a sample document. Extraction covers tables and line items, including across pages, and the vendor states support for 100+ languages and handwriting.

## Workflow and Review

Files are uploaded or emails are forwarded to dedicated addresses, with the option to process the email body, attachments, or both. Mixed PDFs can be split automatically into individual documents and classified to the right schema. Autopilot detects document types and can create a new schema when none matches. Validation rules (for example, totals matching line sums) flag errors, and a human-in-the-loop interface shows fields side by side with the original document for correction before export.

## Developer Access

The docs describe a CLI (installable via pip or npx), a Python SDK, a JavaScript/TypeScript SDK, and a REST API. The API uses a presigned-upload flow followed by task polling, and the SDKs wrap it in a single extract call. Options include auto-splitting, template selection, automatic cleanup after download, exports, and webhooks that deliver completion and failure events. The CLI is positioned for use by AI agents such as Claude Code and Codex.

## Data Handling

The vendor states that customer data is not used to train its models, that data is encrypted at rest and in transit, and that processing takes place in the European Union with GDPR compliance. Users can delete documents at any time.

## Features
- Pre-trained models for 10+ document types
- AI-assisted custom schema generator
- Autopilot extraction for unknown document types
- Automatic splitting of mixed PDFs
- Email body and attachment parsing
- Table and line-item extraction
- Multilingual OCR and handwriting support
- Validation rules
- Human-in-the-loop review
- Webhooks
- Export to Excel, Google Sheets, CSV, JSON
- Team folders and searchable extracted values
- REST API, CLI, Python and JS/TS SDKs

## Integrations
Google Sheets, Excel, QuickBooks, Xero, Webhooks, REST API

## Platforms
WEB, API, CLI, DEVELOPER_SDK

## Pricing
Freemium — Free tier available with paid upgrades

## Links
- Website: https://www.suparse.com
- Documentation: https://www.suparse.com/docs
- EveryDev.ai: https://www.everydev.ai/tools/suparse