Chargemaster Extractor

Extract the facility, service codes (CPT, HCPCS, DRG), descriptions, standard charges, departments, and DRG weights from a hospital chargemaster PDF.

The full guide: Hospital chargemaster service codes and DRG weights

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 Chargemaster Extractor.

What does the chargemaster extractor read?

The schedule document number and its issue, effective, and expiration dates, the issuing facility name and its tax ID or NPI, the currency, the reimbursement method (fee-for-service, DRG, bundled, or per diem), the version number, the payment terms, and the total services count.

Which per-line fields come out?

The service code (CPT, HCPCS, ICD-10-PCS, DRG, or internal), the service description, the standard charge or list price (the chargemaster price), the department code and name, the unit of measure, the modifier code, the DRG weight, the payer discount percent, and the line status.

Are the services returned as a table?

Yes. The chargemaster services table returns each line with its service code, description, standard charge, department code and name, unit of measure, effective and expiration dates, modifier code, and status, so a full price list comes back as rows.

Does it map DRGs and payer contracts?

Yes. A DRG mappings table returns each service code with its DRG code, description, and relative weight, and a payer contracts table returns each payer name, service code, contracted rate, discount percent, and effective date.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. A chargemaster is a facility price list rather than patient data; it 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 document data extraction if you run this for clinical and billing teams, or the extraction API if you are building it in.