Utility Contract Extractor

Extract the supplier, customer, utility type, supply point, tariff, standing charge, unit rate, term, and notice period from a utility supply contract PDF.

The full guide: Supply point ID and kWh unit price from a utility contract

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 Utility Contract Extractor.

What does the utility contract extractor read?

The contract number and date, the effective and expiration dates, the supplier (utility company) name and address, the customer (account holder) name and address, the supply point id (metering point), the utility type (enum, such as electricity, gas, water, heat, or telecom), the contract term, and the notice period to terminate or decline renewal.

How is a utility contract different from a utility bill?

A utility contract is the supply agreement: it sets the tariff, the term, the service address, the standing charge, and the unit rate before any energy is consumed. A utility bill is the periodic invoice that shows metered consumption and the amount due under that contract. For the invoice use the utility bill extractor.

Which tariff and pricing fields come out?

The base fee (standing charge), the unit price and its price unit (such as kWh or m³), the estimated annual consumption and consumption unit, the price adjustment clause, the early termination fee, the total estimated contract value, and the currency each come back as fields.

Are the price components and consumption tiers returned as tables?

Yes. A price components table returns each component name (base fee, energy price, grid fee, taxes and levies), its unit price, unit, and what it applies to; and a consumption tiers table returns each tier with its threshold, unit, and unit price.

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.