Receipt Parsing API

Turn digital receipt PDFs into structured JSON — store, items, totals, payment method — in one API call. Built for text-based PDF receipts, not photos of paper receipts.

Get Free API Key → API Docs
95%+ accuracy
<2s avg parse
10 free docs/mo

Works on text-based PDF receipts (email/export receipts). Does not OCR photographs of paper receipts.

What gets extracted from a receipt

Returned as clean JSON, with a confidence score, in one API call.

✓

store_name / date

Where the purchase happened and when.

✓

total_amount / currency

What was paid, with currency.

✓

payment_method

How it was paid, when stated on the receipt.

✓

tax / tip

Tax and tip amounts, when present.

✓

items

Array of {name, price} for each purchased item.

One API call

No SDK required — plain REST, works from any language.

bash
# Parse a digital receipt PDF
curl -X POST https://ai2json.com/api/v1/parse/document \
  -H "Authorization: Bearer $TOKEN" \
  -F "[email protected]"

# {"doc_type":"receipt","confidence":0.95,"fields":{
#   "store_name":"Online Store Ltd","date":"2026-10-03",
#   "total_amount":64.90,"currency":"EUR","payment_method":"Visa ...1234",
#   "items":[{"name":"Wireless Mouse","price":24.90},{"name":"USB-C Cable","price":9.00}],
#   "tax":5.40,"tip":null}}

Simple, transparent pricing

Start free. Upgrade when you need more.

Free

$0/mo
10 docs/month
  • All document types
  • Structured JSON output
  • API key access
Get Started

Starter

$9/mo
500 docs/month
  • Everything in Free
  • Priority processing
  • Field schema hints
Subscribe

Pro

$29/mo
2,000 docs/month
  • Everything in Starter
  • Batch processing
  • Custom AI prompts
Subscribe

Business

$99/mo
10,000 docs/month
  • Everything in Pro
  • Dedicated support
Subscribe

Frequently Asked Questions

Store name, date, total amount, currency, payment method, tax, tip, and an items array (name, price) for each purchased item.
No — and this is worth being upfront about. AI2JSON reads the text layer of a PDF directly; it does not do OCR on photographs or scanned images. It works well on digital receipts that already exist as PDF — emailed order confirmations, exported e-commerce receipts, digitally issued invoices-as-receipts — not on a phone photo of a paper till receipt.
That's the point of using an AI model instead of a template: there's no per-store template to configure. The same API call works whether the receipt is from a SaaS subscription, an online retailer, or a local vendor, as long as it's a text-based PDF.
The full items array is returned by default; you can use the optional extract_fields parameter to hint which fields matter most for your use case, but the response always includes whatever the model finds.

Ready to try it on your own documents?

Get your API key and parse your first document in under a minute.

Get Free API Key →