Superbill Extractor

Extract provider NPI, patient, payer, service dates, CPT and ICD-10 codes, and charge amounts from a superbill or encounter form. Extraction only, PHI-aware.

The full guide: Read a superbill for out-of-network reimbursement

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 Superbill Extractor.

What is a superbill and how is it different from a professional claim or an EOB?

A superbill is the itemized encounter receipt a provider gives a patient to submit to their insurer for reimbursement — it is not the CMS-1500 professional claim the practice files, nor the EOB the payer returns. The extractor reads the billing provider name, NPI, and tax ID, the patient name, date of birth, and member ID, and the payer name and plan name.

Which codes and service details come out?

The service dates, the place of service, the ICD-10-CM diagnosis codes, and the CPT/HCPCS procedure codes as printed on the form, plus any prior authorization number. The tool transcribes the codes already on the page — it does not assign or generate billing codes.

What amounts does it capture?

The billed amount, the total claim amount, the allowed amount, the paid amount, the patient responsibility (copay, deductible, coinsurance), and the payment amount, along with the claim status, claim type, and adjudication outcome when the superbill shows them.

Does it break out the service lines and diagnoses?

Yes. A service lines table returns each line's number, procedure code and description, units, unit price, service date, charge, allowed, and paid amounts, patient responsibility, and diagnosis pointer, and a diagnoses table lists each diagnosis code, description, sequence, and whether it is principal.

What are the upload limits and is the superbill retained?

One PDF up to 10MB and 100 pages. The form contains PHI; it is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Export as CSV, XLSX, or JSON.

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.