Extract data from certificates of origin
A certificate of origin certifies where goods were manufactured, and it is the document that decides whether a shipment qualifies for a preferential tariff or clears at the standard rate. Customs brokers and trade-compliance teams handle two broad kinds: a generic certificate, often stamped by a chamber of commerce, and a preferential certificate tied to a trade agreement such as the USMCA, which secures a reduced duty. Fields are consistent: the exporter and producer, the consignee, the country of origin, a description of the goods with their Harmonized System classification, and the certifying party with a signature and date.
Difficulty concentrates in the origin determination and the agreement-specific structure. Country of origin is not always the country the goods shipped from, and for a preferential claim it depends on origin criteria (such as a tariff-shift rule or a regional value content threshold) that the certificate references by code. A USMCA certification carries specific data elements and a blanket-period date range that can cover a year of shipments, while a generic chamber-stamped certificate covers a single consignment. HS codes on the certificate have to match the code on the commercial invoice and the customs declaration, and a mismatch holds the shipment. Goods descriptions are free text that has to be tied to the right HS line.
Talonic reads the certificate of origin and returns the exporter, producer, consignee, country of origin, the goods with their HS codes, the origin criteria, and any blanket period. A broker reconciles origin against the invoice and the customs declaration from structured data rather than re-keying each certificate. A certificate issued 2026-04-12 for a shipment from Shenzhen to Long Beach, valued in USD, lets a US broker reconcile the HS code against the commercial invoice and the customs declaration before the goods clear.
What gets extracted from certificates of origin
How extraction works for certificates of origin
Certificates of origin arrive as chamber-stamped scans, exporter PDFs, and trade-agreement certifications, so a generic certificate and a USMCA certification carry different data elements. Talonic classifies the certificate and maps it to the trade-document schema in the Field Registry, which captures the exporter, producer, consignee, country of origin, and the goods with their Harmonized System codes. For a preferential claim, the origin criterion (a tariff-shift rule or a regional value content threshold) and any blanket-period date range are captured, since a USMCA certification can cover a year of shipments while a chamber certificate covers one consignment. HS codes are captured so a broker can reconcile them against the commercial invoice and the customs declaration. Every value returns with a confidence score and pixel-region provenance under DIN SPEC 91491 conformity, so a trade-compliance team can verify origin against the source certificate.
Sample extraction
A chamber-stamped certificate of origin for an ocean shipment
{
"certificate_type": "generic",
"exporter_name": "Shenzhen Anchor Electronics Co.",
"producer_name": "Shenzhen Anchor Electronics Co.",
"consignee_name": "Acme Imports LLC",
"country_of_origin": "China",
"goods": [
{
"description": "Bluetooth speaker modules",
"hs_code": "8518.22",
"quantity": 288
}
],
"origin_criterion": "wholly_obtained",
"blanket_period": null,
"issue_date": "2026-04-12"
}Frequently asked
What is a USMCA certificate of origin?
A USMCA certificate of origin is the preferential certification that claims a reduced duty under the United States, Mexico and Canada agreement, rather than the standard rate a generic chamber-stamped certificate leaves the goods on. It carries specific data elements: the origin criterion, such as a tariff-shift rule or a regional value content threshold, and a blanket-period date range that can cover a year of shipments, where a chamber-stamped certificate covers a single consignment. Classification happens first, so each type is captured on the elements it actually carries.
How does it support reconciliation against other trade documents?
The Harmonized System code and the goods description are captured so a broker can match them against the commercial invoice and the customs declaration, since a code mismatch across documents holds the shipment at the border.
Does country of origin differ from country of export?
Yes, and they are captured separately. The origin is where the goods were produced, which can differ from where they shipped, and a preferential claim depends on the origin rather than the port of loading.
What is a blanket period on a USMCA certification?
It is the date range over which one certification covers repeated shipments of the same goods, so a single USMCA certification can stand for a year of consignments rather than one. The blanket period is captured as its own field. A chamber-stamped certificate issued 2026-04-12 for a shipment from Shenzhen to Long Beach carries none, so its blanket period returns null.
What fields are extracted from certificates of origin?
Talonic returns certificates of origin as schema-validated, typed fields. Common fields include Exporter, Consignee, Country of Origin, Goods Description, and more, each normalized (dates to ISO 8601, amounts as numbers) and mapped to a stable key so the output shape stays the same across layouts.
How accurate is extraction from certificates of origin, and how is confidence reported?
Every extracted cell carries a confidence score from 0.0 to 1.0 and a provenance pointer back to the source page and region, so low-confidence values can be reviewed against the original before the data is trusted downstream. There is no single accuracy number: confidence is reported per field so you can gate on it.
Can I use certificates of origin extraction in production?
Yes. The same engine behind this guide is available as a production REST API and Node SDK with sync, async, and streaming modes, schema versioning, signed webhooks, and EU-resident processing. Start free with an API key, then scale on usage-based pricing.
What does it cost to extract data from certificates of origin?
There is a free tier for prototyping and agent evaluation with no credit card. Paid usage is credit-based at 1,000 credits per euro: page ingestion is 100 credits per page and registry-resolved queries are free. See talonic.com/pricing for current rates.
Ready to extract from your own certificates of origin?
Author note
Reviewed by Talonic engineering, schema review · last reviewed 2026-06-11