Invoice data API

Drop in a supplier invoice and get the header and every line item back as structured data – with the VAT and the totals checked against each other.

PDFScanned PDFJPGPNGAPIExcel (.xlsx)CSVJSON

Start free

Try it on your own invoice

One document, free, right now – no account and no card. You get the fields, the checks and the export, exactly as they come out of the pipeline below.

No document to hand? See it run on a sample – this does not use your free document.

Your document is read and not stored – it never reaches our file storage. Upload only documents you are entitled to share. Privacy Policy · Trust Center

How it works

The whole pipeline, in the order it runs. The document type decides which fields come out and which checks run; the path is the same either way.

The pipeline: read it, extract it, check it, review it, export it – with a failed check routed to a person for review. 1 Read it 2 Extract it 3 Check it 4 Review it 5 Export it anything unresolved goes to a person, not a guess
1

Read it

The invoice is OCR’d and its layout understood – header block, line-item table, totals block – rather than being scraped as loose text.

2

Extract it

The header becomes one record and each line becomes a child record, so the parent/child shape of the document survives into the output.

3

Check it

The arithmetic is re-run: lines, subtotal, VAT and total. An invoice whose own numbers disagree is reported as such.

4

Review it

Low-confidence fields are surfaced beside the original document, so a person corrects a reading instead of re-typing an invoice.

5

Export it

Excel with the header and lines on separate sheets, CSV as two files, or JSON with everything in one object.

What it extracts, and what it checks

Extraction is the easy half. The checks are what turn a converted document into one you can post without reading it twice.

Extracted

  • Supplier name and VAT number
  • Invoice number and dates
  • Customer and purchase-order number
  • Line items – description, quantity, unit price
  • Subtotal, VAT and total
  • Currency

Checked

  • Each line’s quantity × unit price is re-multiplied and compared with the line total.
  • The line totals are re-added and compared with the invoice subtotal.
  • VAT is recalculated at the stated rate and compared with the VAT the invoice prints.
  • Subtotal plus VAT is compared with the invoice total.
  • A VAT number is checked for the right shape before it reaches a ledger.

What goes in, and what comes out

The document on one side, the fields pulled off it on the other – each one checked before it is handed over.

A invoice on the left and the fields extracted from it on the right, each one ticked as checked. Invoice (PDF) Structured, and checked read Supplier name and VAT number Invoice number and dates Customer and purchase-order number Line items – description, quantity, unit price Subtotal, VAT and total

The API is the right answer when this stops being something a person does. The same extraction and the same checks run behind an HTTP call, so the document is read where it already arrives – in your loan origination system, your intake form, your creditors mailbox – instead of somebody downloading it, uploading it here, and carrying the result back by hand.

Same extraction, other formatsCSVJSONExcel

What a flagged document looks like

The original page on one side, the fields read off it on the other. Correct a reading and carry on – the point is that nobody re-types a document to fix one number.

An Automize approval: the supplier invoice PDF beside the fields extracted from it, with approve and reject controls.
A supplier invoice on the same review screen – the document beside what was read off it, to approve, correct, or send back.

And then it does not have to stop there

A spreadsheet is the end of the job for most converters. Here it is a step: the same structured output can go straight into a process that posts it to your ledger, matches it against a purchase order, files the original, and asks a person only about the exceptions.

See what a Digital Worker does with it

Related tools

Statement extractor

Drop in a PDF or a photograph of a bank statement and get every transaction back as a spreadsheet – dates, descriptions, debits, credits and the running balance.

Questions

Yes, because an invoice is a parent with children and flattening it loses that. Excel gets an Invoices sheet and a Line Items sheet joined by the invoice number, CSV gets two files, and JSON keeps the line items nested inside the invoice. That is what makes the output importable rather than merely readable.
It recalculates it. VAT is re-derived at the rate stated on the document and compared with the VAT printed on it, and the subtotal and total are re-added the same way. An invoice that does not add up is flagged – which is usually a reading error worth catching, and occasionally an invoice error worth catching.
The currency is extracted as a field and the arithmetic is checked in that currency. Nothing is converted – a conversion would need a rate and a date that the invoice does not state.
It does not, which is the point: the same extraction, the same checks and the same canonical JSON. What changes is who calls it. Authentication is a scoped API key, the call is synchronous for a single document and asynchronous with a callback for a batch.

Try it on your own document

Create a free Automize company and upload a document. Extraction, the checks and the exports are all in the platform – and when the same document arrives every month, the process that reads it can post it too.

Start free See pricing