Contractual Purchase Order Extractor

Extract the buyer, supplier, ship-to, line items, totals, payment terms, and the contractual clauses from a contractual purchase order PDF. No signup.

The full guide: Termination for convenience in a master purchase order

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Contractual Purchase Order Extractor.

How is this different from a plain purchase order extractor?

It reads the contractual purchase order: beyond the line items and totals, it captures the negotiated legal clauses (anti-assignment, termination for convenience, cap on liability, most-favored-nation, exclusivity, insurance, audit rights, and minimum commitment), following the CUAD clause taxonomy.

Are the ordered items itemized?

Yes. The line items table returns each item with its item number, description, quantity, unit of measure, unit price, line amount, tax rate, and line tax, so the order body comes back ready to reconcile against the totals.

Which parties and money fields come out?

The buyer name, address, and contact, the supplier and the ship-to party, the subtotal, tax amount, and total amount with currency, the payment terms and incoterms, the reference to any framework or contract number, and the supplier IBAN and BIC.

Does it return the terms and conditions?

The terms and conditions table returns each clause with its title, full text, and CUAD clause category, and a charges table returns any shipping, handling, or discount charge with its type, amount, and description.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The purchase order is processed via the Talonic API for extraction, is not retained for training, and is not shared.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See document data extraction if you run this for legal and commercial teams, or the extraction API if you are building it in.