Expenses, bookkeeping, reimbursements — get a receipt's data as JSON. Text in the browser, structured fields through the API.
Structure options shape the JSON output.
Send a PDF, get the same structured output back, plus OCR for scanned files and table extraction. Batch-ready. From $29/month.
Read the API docs →Receipts are small but awkward — odd sizes, tight layouts, faded print. This tool reads a text-based receipt PDF and returns its contents as JSON in your browser, no upload. It's the quick path when you just need the text as data.
For expense and bookkeeping workflows you usually want the fields — merchant, date, tax, total, and line items — not the raw text. That's structured extraction on the API, which returns typed JSON ready to drop into an expense report or ledger.
A photo has no text layer, so it needs OCR. The browser tool handles text-based receipt PDFs; the API can OCR photos and scans.
Typically merchant name, date and time, payment method, subtotal, tax, tip, total, and line items with description and price.
The browser tool gives you the receipt's text as JSON. The API extracts named fields and line items as structured JSON.
Use the API to convert each receipt to JSON, then map the fields to your expense tool's format. It's designed for automated pipelines.
Clean digital receipts extract well. Faded thermal prints and skewed photos are harder and benefit from a review step.
Yes, through the API — send them as they come in and store the JSON.
An OCR library gives you raw text you still have to parse. This returns the text as JSON in the browser, and named fields through the API.
Not for free browser extraction of text-based PDFs. OCR and structured extraction run on the API.