Extract merchant, date, payment method, subtotal, tax, tip and total from a receipt PDF or scan, plus each line item as rows. Free CSV, XLSX or JSON export.
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
The merchant name and address, the receipt or transaction number, the transaction date and time, the payment method and the last four digits of the card, and the money fields — subtotal, tax, tip, total, and currency. It also captures every purchased item as its own row.
As a real table. The line items return as an array with one object per item purchased, and each row has named columns — the item description, the quantity, the unit price, and the line amount — so a grocery or restaurant receipt comes back as rows you can total and audit. It exports as CSV, XLSX or JSON rows rather than one text blob. This is the point of the rebuilt tool: the old version collapsed the items into a single summary line.
Retail and grocery receipts, restaurant and bar checks, fuel and travel receipts, and hotel folios. It reads both digitally generated PDFs and scanned or photographed receipts (via OCR), and the field labels are read in several languages (German Händler / MwSt / Gesamtbetrag, Spanish comercio / IVA / total, French commerçant / TVA / total).
Yes. Because the merchant, date, payment method, subtotal, tax, tip and total all come back as their own fields, and the purchased items as rows, a receipt drops straight into an expense report or bookkeeping export. Point it at each receipt and download the structured data as CSV or XLSX.
PDF only, up to 10MB and 100 pages. The receipt is processed via the Talonic API for extraction only, is not retained for training, and is not shared.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See invoice data extraction if you run this for finance and AP teams, or the extraction API if you are building it in.