Extract utility bills to structured JSON
Utility bills for electric, gas, water, and internet serve as proof of address in KYC, identity confirmation, and lending workflows. Every provider formats bills differently. Sensible converts utility bill data into structured JSON for address verification and compliance.
Why utility bills defeat template-based extraction
Thousands of providers each format bills differently. Mergers and system changes multiply the count.
Account numbers here. Addresses there. Every electric, gas, water, and telecom provider places fields in different locations. Per-provider configurations handle major utilities; LLM parsing covers the long tail without custom setup.
Electric, gas, water, sewer: some providers bundle all services on one bill with separate sections. Each service type is identified and its charges, usage, and rate detail extracted individually.
Utility bills present usage data with tiered rates, demand charges, and time-of-use breakdowns in tables that vary by provider. Extracting the rate structure alongside consumption data requires understanding each utility's billing format. Sensible parses these tables into structured usage and charge data.
Fields we extract
Address and account fields cover KYC and proof-of-address requirements. Add usage fields as needed.
Account holder name, account number, service address, mailing address, utility provider name, bill date, due date
Current charges, previous balance, payments received, amount due, usage quantity (kWh/therms/gallons), usage period, rate/tariff
Service start date, statement period, provider contact info, meter number, service type (electric/gas/water/internet)
Telecom provider bill with service plan, equipment charges, and account details.
Monthly electric utility bill with usage (kWh), rates, and service address.
Municipal water and sewer bill with consumption, rates, and service period.
Natural gas utility bill with therms consumed, delivery charges, and account info.
Supported utility types
Sensible processes utility bills from any provider worldwide. The hybrid approach handles format diversity across thousands of providers while deterministic rules enforce the output your KYC or accounting system expects.
Electric, natural gas, water/sewer, internet/broadband, phone/mobile, cable/satellite, waste/recycling
Investor-owned utilities (PG&E, ConEd, Duke Energy), municipal utilities, cooperatives, telecom providers (AT&T, Comcast, Verizon)



Common Questions
Answers about provider support, address verification, and multi-service bill handling.
Yes. Sensible extracts the account holder name, service address, billing date, and provider name from utility bills. These fields support address verification and identity confirmation workflows.
Sensible extracts account number, billing period, previous balance, payments received, current charges, and amount due. Usage data (kWh, therms, gallons) is also captured when present.
Sensible captures the service address, mailing address, account holder name, and account number. This supports proof-of-address verification in KYC workflows.
Yes. Sensible processes electric, gas, water, internet, and phone bills from any provider. The hybrid extraction approach adapts to each provider's format.
Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.
Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.
Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.
Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.
Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.
Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.
Sensible provides REST APIs and SDKs for Python and Node.js. Most integrations take a few hours. Webhooks, Zapier, and direct API calls are all supported.
Sensible processes PDFs (native or scanned), Microsoft Word (DOC, DOCX), spreadsheets (XLSX, XLS, CSV), single-page images (JPEG, PNG), multi-page images (TIFF), and email bodies with attachments.
Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.
Processing speed depends on document size, page count, OCR requirements, and which extraction methods are used. Simple single-page documents process in seconds. Larger or more complex documents that use LLM-based extraction take longer.
