FATCA and CRS Filing Extractor

Extract the reporting institution GIIN, account holders, tax residency, balances, and reportable-account flags from a FATCA or CRS filing PDF. No signup.

The full guide: GIIN, tax residency, and TINs on a FATCA or CRS filing

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 FATCA and CRS Filing Extractor.

What does the FATCA and CRS extractor read about the reporting institution?

The reporting entity name, its GIIN (Global Intermediary Identification Number), and its tax ID, the reporting period end date, the type of financial institution, and the filing document number and date.

Are the reported accounts returned as tables?

Yes. The accounts table returns the account number, type, status, balance, currency, opened and closed dates, IBAN, and BIC; the account holders table returns the holder name, tax residency, tax ID, FATCA and CRS classification, and the reportable-account flag; and separate controlling persons and account income tables come back too.

Does it capture the FATCA and CRS classifications?

The FATCA classification (such as US Person, FFI, NFFE, Passive NFE, or Exempt Beneficial Owner), the CRS classification, the reportable-account indicator, the high-value-account flag, the Section 901(j) status, and the entity non-reporting status are each read.

Which income figures are extracted?

Gross interest paid, gross dividends paid, gross capital gains paid, other income paid, and the aggregate income amount per account, in the account currency, alongside the KYC completion date and the next review date.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The filing 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.