Claim Settlement Extractor

Extract the policy, coverage, approved amount, payment, settlement status, and payment breakdown from a claim settlement or payment PDF. No signup.

The full guide: Claim settlement statements: net payment and deductions

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 Claim Settlement Extractor.

What does the claim settlement extractor read?

The document number and date, the insured name and address, the policy number and its effective and expiration dates, the insurer name and NAIC number, the coverage type (enum), the incident date, and the claim description.

Which settlement and payment fields come out?

The original claim amount, the approved amount, the deductible, the payment amount and currency, the payment method (enum, such as check, transfer, or wire), the payment date, and the settlement status (enum, such as approved, pending, denied, or partial).

How are the charges, deductions, and payment split returned as tables?

A claim charges table returns each charge type, description, amount, and currency; a deductions table returns each deduction type, description, amount, and currency; and a payment breakdown table returns each line item, amount, currency, and payment status, so the net payment reconciles against the approved amount.

How is this different from an adjuster report?

A claim settlement records the final payment on a claim, with the approved amount, deductions, and payment breakdown. An adjuster report captures the earlier loss assessment and damage estimate. For that assessment stage, use the adjuster report extractor.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The document is processed via the Talonic API for extraction only, 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 underwriting and claims teams, or the extraction API if you are building it in.