Customs Declaration Extractor

Pull the exporter, importer, commodity codes, declared value, and duties from a customs declaration or entry PDF, with duty tables. No signup.

The full guide: Customs declaration entry summary, HS codes and duty

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 Customs Declaration Extractor.

Which parties does the customs declaration extractor read?

The exporter, importer, declarant, and representative, each with a name and tax ID or EORI number, so the roles on an import or export entry are captured for compliance records.

Are the goods items returned line by line?

Yes. The goods items table returns the commodity code, CUS code, country of origin, country of preferential origin, preference, valuation method, item price, net mass, package type and count, and statistical value for each item on the entry.

How are duties and charges captured?

The total duty amount, valuation method, and total declared value with currency come back as fields, and the taxes and duties table returns each duty type with its rate, amount, and basis, alongside a charges table for freight and insurance.

Does it read the movement and declaration details?

Country of origin, destination, and dispatch, the port of entry, location of goods, incoterms, transport mode, declaration type, additional declaration type, and declaration status are each read, plus references to previous and supporting documents.

What file limits apply and is the entry kept?

PDF only, up to 10MB and 100 pages. The declaration 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 PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.