Extract data from shipping manifests
A shipping manifest is the single list of everything a carrier is moving on one conveyance. Where a Bill of Lading covers one consignment and a packing list covers the cartons inside one shipment, the manifest sits one level up: it enumerates every consignment loaded onto a named vessel, aircraft, or truck for a given voyage. A liner agent closing out the EVER LEADER on voyage 132W out of CNSHA Shanghai files a cargo manifest listing hundreds of consignments across dozens of containers, and a US Customs unit ingests the same data as a CUSCAR declaration before the ship berths at USLAX Los Angeles. Each manifest line ties a consignment to its shipper, consignee, container and seal, package count, gross weight, and HS commodity code, so the manifest is what a port agent, a consolidator, and a customs authority all read to know what is aboard.
Scale and heterogeneity live in one document. A manifest can carry a single house consignment or several hundred, and the granularity shifts between the header, the conveyance, the carrier, the ports, the voyage, and the repeating consignment block. Container numbers follow ISO 6346, yet a single manifest mixes 20GP, 40HC, and reefer units, and a consignment can span two containers or share one with three others. Gross mass appears per line in kilograms on an ocean manifest and in pounds on a domestic parcel manifest, package type codes follow UN/ECE Recommendation 21, and freight terms toggle between prepaid and collect per consignment. A consolidated manifest interleaves master and house references that a downstream system has to keep linked.
Talonic reads the manifest and returns the conveyance header once, then every consignment as a structured row carrying its shipper, consignee, notify party, container and seal, package count and type, gross weight, measurement, and commodity code. Container identifiers are checked by their ISO 6346 check digit, weights are normalized to a canonical value with an explicit unit, and prepaid versus collect stays on each line. A manifest for hundreds of consignments closing 2026-04-12 arrives as a row per consignment that a port community system or a customs filing can load, whether the source is a clean carrier PDF or a scanned agent copy.
What gets extracted from shipping manifests
How extraction works for shipping manifests
Shipping manifests come off carrier and terminal operating systems, consolidator TMS platforms, and forwarder software, so an ocean cargo manifest, an air consolidation manifest, and a domestic parcel manifest carry the same idea in different layouts. Talonic classifies the document and maps it to the transport model in the Field Registry, which holds the conveyance header once and the repeating consignment block as a linked array rather than a flat table. Container identifiers are checked against the ISO 6346 check digit, gross mass is normalized to a canonical value plus an explicit unit, and package type codes follow UN/ECE Recommendation 21. Master and house references are kept linked when a consolidation shows both. Each value returns with a confidence score and a pixel-region pointer into the source page under DIN SPEC 91491, so a port agent or a customs filer can verify a container or a weight against the manifest before the vessel is worked.
Sample extraction
A cargo manifest with two consignments on one voyage
{
"document_number": "MAN-2026-132W",
"document_date": "2026-04-12",
"carrier": "Oceanic Lines Ltd.",
"vessel_name": "EVER LEADER",
"voyage_number": "132W",
"port_of_loading": "CNSHA Shanghai",
"port_of_discharge": "USLAX Los Angeles",
"currency": "USD",
"total_packages": 640,
"total_weight": 9860,
"weight_unit": "KG",
"freight_and_charges": "Prepaid",
"line_items": [
{
"consignee": "Acme Imports LLC",
"container_number": "MSKU7654321",
"container_type": "40HC",
"seal_number": "0099213",
"number_of_packages": 288,
"package_type": "CTN",
"gross_mass": 4820,
"commodity_code": "8479.89"
},
{
"consignee": "Harbor Retail Group",
"container_number": "TCLU4412208",
"container_type": "40HC",
"seal_number": "0099244",
"number_of_packages": 352,
"package_type": "CTN",
"gross_mass": 5040,
"commodity_code": "8518.22"
}
]
}Frequently asked
What is a shipping manifest, and how is it different from a Bill of Lading?
A shipping manifest is the single list of everything a carrier is moving on one conveyance, so it enumerates every consignment loaded onto a named vessel, aircraft, or truck for a given voyage. A Bill of Lading covers a single consignment and can act as a document of title, and a packing list sits a level below again, covering the cartons inside one shipment. Talonic reads each on its own schema.
Does it handle hundreds of consignments on one manifest?
Yes. The consignment block returns as an ordered array, so a manifest covering 340 consignments comes back as 340 rows, each with its shipper, consignee, container, package count, and gross weight.
Are the container numbers validated?
Container identifiers are checked against the ISO 6346 check digit during extraction, and a mismatch is flagged in the confidence output so a port agent can verify against the physical unit.
Can it read a customs cargo manifest?
Yes. A cargo declaration filed as a CUSCAR or an IFTMIN message rendered to PDF reads through the same schema. Native EDIFACT message ingest runs through a separate API path.
What fields are extracted from shipping manifests?
Talonic returns shipping manifests as schema-validated, typed fields. Common fields include Manifest Number, Manifest Date, Carrier, Vessel / Voyage, 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 shipping manifests, 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 shipping manifests 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 shipping manifests?
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 shipping manifests?
- GDPR
- HIPAA
- ISO 27001 / 42001 aligned
- DIN SPEC 91491 co-author
- EU-resident infrastructure
Author note
Reviewed by Talonic engineering · last reviewed 2026-07-07