Xtracta — API-First Document Data Extraction
New Zealand-based API-first document processing platform serving 1,000+ global users with deep learning research and PEPPOL e-invoicing capabilities.
How Xtracta OCR Technology Works
Xtracta has evolved from a "quiet infrastructure provider" to an active challenger against ABBYY, Rossum, and UiPath in the mid-market IDP segment. The Auckland-based company processes over 10 million pages monthly through its API-first platform, targeting 30% annual ARR growth by 2026 following a strategic go-to-market transformation.
Since early 2022, Xtracta has been conducting deep learning research developing biological brain-mimicking approaches for data extraction, moving beyond traditional statistical methods common in the IDP market. In June 2023, the company joined the PEPPOL e-invoicing network as an access point provider, enabling software partners to offer structured e-invoicing alongside traditional PDF/JPG document processing.
Xtracta positions itself around "invisible intelligence" - seamless data automation integration within customer platforms rather than standalone tools. This API-first approach targets mid-market ISVs and operations teams who prioritize "trust, simplicity, and speed to value" over pure OCR technology capabilities, according to the Flux B2B case study.
Xtracta Platform Features
- API-First Architecture: Specialized APIs for invoices, receipts, contracts, passports/ID cards, bank statements, remittance advice, and purchase orders
- Template-Free Xtracta OCR: AI and machine learning across dozens of languages without pre-defined templates
- Deep Learning Research: Biological brain-mimicking approaches for data extraction since 2022
- PEPPOL E-invoicing: Access point provider for structured e-invoicing network integration
- High-Volume Processing: 10+ million pages monthly processing capacity
- Self-Learning Capabilities: Continuous improvement through machine learning
- Multi-Format Support: PDFs, images, and scanned documents
- Custom Data Validation: Business rules for verifying extracted information
- Cloud and On-Premise Deployment: Flexible implementation options
Use Cases
Accounts Payable Automation
Andrew Butchart, Financial Controller at Scandinavian Vehicle Distributors, reports: "We estimate MYOB Greentree eDocs, powered by Xtracta is reducing time spent on invoice entry by 40%, freeing up two to three days a month for our Accounts Payable person." The platform automatically extracts header data and line-item details from supplier invoices without template configuration.
High-Volume Invoice Processing
Rebecca Payne, Accounts Payable at Ryman Healthcare, processes "on average 15,000 invoices every month" and states: "Xtracta-powered eDocs is saving us hours of work each week." Paul Harrington, Group Sales and Marketing Manager at McCallums Group, quantifies the impact: "We are saving 90 hours per month. I can see valid performance indicators much earlier."
E-invoicing Integration
Through PEPPOL network membership, software partners can offer structured e-invoicing capabilities alongside traditional document processing, though Xtracta expects initially slow adoption of e-invoicing standards.
Xtracta Pricing and Technical Specifications
| Feature | Specification |
|---|---|
| Deployment Options | Cloud SaaS, On-Premise, Hybrid |
| Integration Methods | REST API, Webhooks, Pre-built Connectors |
| Supported Formats | PDF, TIFF, JPEG, PNG, BMP |
| Processing Volume | 10+ million pages monthly capacity |
| AI Technologies | Deep Learning, Machine Learning, Computer Vision, NLP |
| Language Support | Dozens of languages |
| E-invoicing | PEPPOL access point provider |
| Document Types | Invoices, receipts, contracts, ID cards, bank statements, purchase orders |
| Architecture | API-first, template-free processing |
| Research Focus | Biological brain-mimicking extraction methods |
Resources
Company Information
Level 5/45 O'Rorke Road
1061 Auckland, New Zealand
Web: https://xtracta.com
Email: info@xtracta.com
Tel: +64 9 951 0448