Invofox

Invofox is a document data extraction API. It takes PDFs and images of invoices, receipts, payslips, bank statements, tax forms and custom document types, runs them through OCR and machine learning models, and returns structured JSON. Files containing several documents are classified and split automatically, every field carries a confidence score, and corrections feed back into the models so accuracy improves over time. It is built for engineering teams that need to process documents at volume, in accounts payable, mortgage and lending, insurance, healthcare, manufacturing, legal, payroll, logistics and automotive settings. Pretrained models cover the common document types and custom schemas handle the rest. Security options include a zero retention mode that deletes documents after delivery, on premises and VPC deployment, and SOC 2 Type II, ISO 27001, GDPR and HIPAA compliance. The billing model is unusual: customers pay only for pages extracted correctly, and pages the system gets wrong are credited. Pricing is published as four plans. Free is $0 and includes 500 pages, the pretrained models for invoices, receipts, utility bills, tickets and payslips, REST API access and community support, with no card required. Starter starts at $500 per month billed annually for up to 5,000 pages per month with email support and a 99.9 percent uptime SLA. Scale is custom with volume discounts, and adds advanced extraction models, custom field mapping, priority support and a dedicated account manager. Enterprise is custom for 250,000 or more pages per month and adds custom model training, custom SLAs and the zero retention policy. Invofox notes that all prices are estimates that vary with document complexity, volume and integration needs.