system readyinvoice in, structured data out

Invoice in.
Clean data out.
Automatically.

Drop in or forward any invoice and datahone reads it like a person — supplier, line items, totals, VAT, dates, PO numbers — into clean, structured JSON. No templates to maintain, any layout, any currency. Delivered by webhook, the REST API, or a JSON, CSV, or XLSX download.

No card · 20 free pages / moPDF, scan, or photoAny layout, any currency
Push clean invoice data into the tools your finance team already runs. Connect via webhook or the REST API.
automate your accounts payable

What is invoice OCR?

Invoice OCR turns a picture of an invoice — a PDF, a scan, a phone photo — into structured, editable data, so no one has to retype it. datahone goes a step past classic OCR: instead of just reading characters, it understands what each part of the document means.

It identifies the supplier, the invoice and PO numbers, the dates, every line item, and the totals and tax — across any layout, in any language, in any currency — and hands them back as clean JSON your accounting tool can ingest. No per-supplier templates, no rules to maintain.

Any layoutOne model reads every supplier’s format — no template setup, and nothing breaks when a layout changes.
Line by lineVariable-length item tables come back as separate rows, with quantities, prices, and totals.
Books-readyDates, currencies, and tax normalised to one shape — ready to post, reconcile, and pay.
simple workflow

How invoice OCR works. Three steps.

Send datahone an invoice, tell it where the data should go once, and every invoice after that runs on autopilot. You only ever touch three surfaces.

Step 01 · send

Send your invoices

Upload a PDF or scan, forward supplier emails to a dedicated address, or push them through the API. Photos and scanned paper work too — datahone reads them the same way.

INV-12345 · ACME Inc.pdf invoice · parsing…
Step 02 · extract

AI reads the invoice

datahone handles varying layouts, scanned documents, and complex line-item tables across different suppliers — pulling supplier, totals, VAT, dates, and every line. Low-confidence fields wait for review.

supplierACME Inc.
total_gbp1,540.80
vat256.80
confidence0.98
Step 03 · export

Send it where it belongs

Clean JSON streams to any webhook you run — in real time, ready for the accounting tool or ERP you already use. Pull it from the REST API, download CSV or XLSX, or review it in the dashboard before it posts.

GETapi/v1/exports?format=csv202 queued
GETapi/v1/documents/:id/output200 ok
POST/datahone/webhook200 ok
flexible data capture

Watch it read an invoice.

Point datahone at any invoice and it lifts every field into structured JSON — supplier, dates, references, line items, totals, and tax. Start from the common fields below, then add, rename, or remove whatever your books need.

INVOICEACME Inc.
456 1st Street, Newtown, USA
Invoice no.
INV-12345
PO number
PO-67890
Invoice date
2026-01-01
Bill to
John Doe
123 Main Street, Anytown, USA
DescriptionPriceQtyTotal
Design retainer300.002600.00
Hosting (annual)240.001240.00
Support hours60.009444.00
Subtotal1,284.00
VAT (20%)256.80
Total due£1,540.80
invoice.jsonextracting
"invoiceNumber" "INV-12345" // 0.99 "poNumber" "PO-67890" "invoiceDate" "2026-01-01" "supplierName" "ACME Inc." "customerName" "John Doe" "lineItems" "desc" "Design retainer" "qty" 2 "total" 600.00 "desc" "Hosting (annual)" "qty" 1 "total" 240.00 "desc" "Support hours" "qty" 9 "total" 444.00 "subtotalAmount" 1284.00 "taxAmount" 256.80 "totalAmount" 1540.80 "currency" "GBP" "status" "review_passed"
what datahone pulls from an invoice

Every field that matters. Every supplier.

From a one-line receipt to a 40-line trade invoice, datahone returns the same clean, structured record — ready to post, reconcile, and pay.

01

Line items, every row

Variable-length item tables come back as separate, structured rows — description, quantity, unit price, and line total — however many lines the invoice runs to.

02

Totals & tax

Subtotal, discounts, VAT or sales tax, shipping, and the grand total — captured and reconciled, so what you post matches what you owe.

03

Supplier & bill-to

Supplier name and address, your billing entity, contact details, and bank or payment references — the header data that tells your ledger who and where.

04

Multi-currency, normalised

Dates, currencies, and number formats come back in one consistent shape — ISO dates, decimal amounts, currency codes — whatever the supplier’s locale.

05

PO matching

Pull the PO number off the invoice and match it against your open purchase orders — so two- and three-way matching happens before anything reaches approval.

06

Bulk invoice runs

Send a whole month’s stack at once. datahone processes them in parallel, flags the low-confidence ones for review, and exports the rest straight through.

let AI do the boring work

Why teams run invoices through datahone.

It puts accounts-payable data capture on autopilot, so your finance team spends its time on the work that actually needs judgement.

Hours back, every week

Stop keying invoices line by line. datahone reads a full invoice in seconds and posts it for review, so the stack that used to take a morning clears itself.

Seconds per invoice, not minutes

Fewer keying errors

Every field carries a confidence score; anything uncertain is held in a review queue for a person to confirm. Nothing questionable posts to your ledger unchecked.

Review queue on low confidence

Lower cost to process

Handle peak-period volume without temp staff or overtime. You pay per page with a hard cap on every tier — overages are blocked, never billed by surprise.

Per page, hard-capped

Secure & compliant

Invoices and the data inside them are encrypted in transit and at rest, scoped to your account, and never used to train shared models. EU-hosted, GDPR-aligned.

EU-hosted, encrypted
questions

Invoice OCR, answered.

Q · 01

PDFs (digital or scanned), images and photos (JPG, PNG, HEIC), and invoices arriving as email attachments. Whether it's a clean export or a phone snap of a paper invoice, datahone reads it the same way.

Q · 02

Three ways: upload files in the dashboard, forward supplier emails to a dedicated address (auto-forwarding works), or push them through the REST API. Most teams set up email forwarding once and forget about it.

Q · 03

Yes. Variable-length item tables come back as separate structured rows — description, quantity, unit price, and line total — however many lines the invoice has, and even when the column layout differs between suppliers.

Q · 04

No. There are no per-supplier templates or rules to set up. One model reads every layout in context, so a new supplier or a changed invoice design doesn't break anything.

Q · 05

It extracts the PO number from the invoice so you can match it against your open purchase orders — supporting two- and three-way matching before an invoice reaches approval. Push the data to your ERP via webhook or API to close the loop.

Q · 06

To any webhook endpoint you run, pulled from the REST API, or downloaded as JSON, CSV, or XLSX, ready for the accounting tool or ERP you already use. Review it in the dashboard before it posts. Most teams wire up a destination in minutes.

Q · 07

Every field comes back with a confidence score; low-confidence fields are held in a review queue for a person to confirm before posting. Dates, currencies, and number formats are normalised to one consistent shape, in any language.

Q · 08

Per page, with a hard cap on every tier — one invoice page is one page. When you hit your limit the next page is blocked rather than silently billed, so a bulk run can never produce a surprise bill. See pricing →

get started

Stop keying invoices by hand.

Drop in an invoice and watch datahone hand it back as clean, structured data — supplier, line items, totals, and tax, ready for your books. Free in minutes, no card required.

Any layout, no templatesLine items & taxStraight to your books