Contract Extractor

Upload any contract PDF and extract the key terms: parties, dates, governing law, termination, liability, IP, and total value. Free, no signup.

The full guides: Confidentiality scope and term from a mutual NDA · Base salary and equity vesting in an offer letter

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 Contract Extractor.

What does the Contract Extractor extract?

The contract title and best-fit contract type, the effective (commencement) date and the execution (signing) date, the currency and the total contract value, and a plain-language summary of the contract term — plus the full roster of contracting parties.

Do the contracting parties come back as a table rather than a blob?

Yes. The parties return as a structured table with one row per named party and named columns for the fields on each party — the party name, the role it plays in the contract (such as buyer and seller, disclosing and receiving, licensor and licensee, or landlord and tenant), the legal entity type where stated, and the address or registered office — so they export as CSV rows rather than one text blob.

Which contract clauses does it capture?

The governing law and the dispute-resolution venue, the termination rights and notice terms, and the confidentiality, indemnity, limitation-of-liability, and intellectual-property clauses each come back as their own field, read as written on the document.

Does it read non-English and EU-format contracts?

Yes. Field synonyms cover German, Spanish, and French labels such as Vertragsparteien, Kündigung, anwendbares Recht, Gerichtsstand, resolución de disputas, and droit applicable, and dates are read against EU formats like 24.06.2026 as well as US formats.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. The contract 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 legal and commercial teams, or the extraction API if you are building it in.