Purchase order OCR API
Extract PO numbers, buyer, ship-to and line items from purchase orders so they can be matched against invoices.
Result
Your Markdown or JSON shows up here.
What makes purchase orders hard to read
- Long line-item tables split across pages
- SKUs and part numbers with easily confused characters
- Terms and delivery notes buried in free text
What you can pull out
purchase-order fields
{
"po_number": "PO-88213",
"buyer": "Coastal Builders Pty Ltd",
"vendor": "Steelform Industries",
"order_date": "2026-10-28",
"ship_to": "Unit 4, 18 Dock St, Fremantle WA",
"line_items[]": "sku, description, qty, unit_price",
"total": "14,760.00",
"currency": "AUD"
}Best models for purchase orders
1Reducto ParseHigh-accuracy parsing for complex financial and legal documents, with citations.
reducto/parse20 credits / page2Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 credits / page3Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / pageCall it from your code
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "reducto/parse",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'