By document type / Bill of lading
Send any PDF bill of lading — ocean, truck, or rail, digital or scanned. The data extractor returns carrier, consignee, ports, container IDs, and freight terms as typed JSON.
Sample invoice
From
Pacific Maritime Lines
Bill to
Globex Distribution Centers
Extracted schema
Sample JSON
{ "document_type": "bill-of-lading", "bol_number": "BOL-2049-PMX", "carrier": "Pacific Maritime Lines", "shipper": "Pacific Maritime Lines", "consignee": "Globex Distribution Centers", "bol_date": "2026-05-10", "freight_total": 4200, "currency": "USD", "line_items": [ { "sku": "CONT-PMX2049", "description": "40ft container · 12,400 kg · electronics", "quantity": 1, "unit_price": 2800, "amount": 2800 }, { "sku": "CONT-PMX2050", "description": "40ft container · 9,800 kg · electronics", "quantity": 1, "unit_price": 1400, "amount": 1400 } ] }
Typed JSON matching the schema you send: BoL number and date, carrier and SCAC, shipper, consignee, vessel/voyage, ports, container and seal numbers, freight terms, and per-item weight and quantity rows — ready for your TMS or ERP.
Yes. Most BoLs arrive as scans, photos, or faxes. OCR runs automatically when the PDF has no text layer, and skewed or low-resolution pages are handled before extraction.
Yes. Straight, ocean, and inland BoLs share the core schema; fields that do not apply (like vessel_voyage on a truck BoL) come back null instead of guessed.
Yes. The schema covers both; container_numbers may be empty on a master BoL.
No. The parser reads each PDF’s layout directly — no zone-drawing and no per-carrier template library to maintain as layouts change.
Extraction is priced per page. The free tier covers the first 100 pages.