What the analyzer does
Medical Bill Reader accepts an uploaded medical bill or Explanation of Benefits document, sends it to an AI model for analysis, and returns a plain-English breakdown organized into five sections: what the bill is for, a breakdown of the charges, what you owe, potential issues to review, and what to do next. The output is a written explanation, not a diagnosis or a payment decision.
What model powers the analysis
The analyzer calls the Anthropic Claude API. The current model is claude-opus-4-7, Anthropic's general-purpose multimodal model. The API request is made server-side from a Next.js API route. The Anthropic API key is read from a Vercel environment variable and is never embedded in client code.
The model receives the uploaded file (image or PDF) and a single prompt instructing it to act as a medical billing expert and structure its response under the five fixed section headings above. The model uses its general training to recognize billing codes, common charge patterns, and typical EOB layouts. It does not look up codes against a live database, does not read your insurance plan documents, and does not have access to your medical history.
What the analyzer identifies
The model is asked to surface the items most useful to a patient:
- Procedure and service codes such as CPT (Current Procedural Terminology), HCPCS Level II, ICD-10-CM diagnosis codes, and NDC drug codes when present.
- Service dates and provider information as printed on the bill.
- Charge structure: total charges, the insurer-allowed or negotiated amount, plan payment, and patient responsibility (deductible, coinsurance, copay).
- Patterns that may indicate billing errors: duplicate line items, charges inconsistent with the listed diagnosis, suspected unbundling of services, or charges for services not commonly delivered together. These are pattern observations from the AI, not certified findings.
For a glossary of the specific code systems and abbreviations the analyzer references, see the codes explained page.
How bill data is handled
Medical bills contain sensitive personal and health information. Handling reflects that:
- Server-side processing: the file is sent over HTTPS to a Next.js API route on Vercel, which forwards the content to the Anthropic API and returns the response.
- No persistence: the bill content is held in memory only for the duration of a single request. The application does not write the bill to a database, an object store, or a log file. The response text is returned to your browser and is not retained server-side either.
- No identifiers stored: the application does not require an account, does not capture your name, and does not link uploads to a user identity.
- No advertising data flow: bill content is never passed to any advertising system, analytics provider, or third-party tracker. Analysis pages use a strict referrer policy so that page URLs cannot leak to third parties.
- Anthropic processing: the file is processed by Anthropic's API to produce the response. Per Anthropic's published policies, API inputs and outputs are not used to train their models by default. Refer to Anthropic's data usage and retention policy for the current details.
Honest limitations
The tool is useful as a first-pass plain-English explanation. It is not a substitute for professional review. Specifically:
- The analysis is informational, not medical or financial advice.
- The model can misread poor-quality scans, low-resolution photos, handwriting, or heavily redacted documents.
- The model cannot detect every form of billing fraud or error. Sophisticated upcoding, unbundling, or balance-billing issues often require a billing advocate to confirm.
- The tool does not have access to the contracted reimbursement rate that the provider negotiated with your specific insurance plan. It cannot tell you what the "right" price should have been.
- Insurance regulations and patient protections vary by state and by plan type (employer, ACA, Medicare, Medicaid, TRICARE). The model cannot account for those differences.
- The model can hallucinate. Verify any specific code or amount it references against your itemized bill before acting on it.
Why this matters
Medical billing errors are common and costly. Patient advocacy organizations and academic studies have for years documented significant error rates on hospital and provider statements, alongside widespread confusion about what charges mean and which ones can be appealed. Patients have rights they often do not know about: the right to an itemized bill, the right to appeal a denied claim, and protections under the federal No Surprises Act for certain out-of-network charges. The goal of this tool is to lower the barrier to reading what is actually on a bill so those rights can be used.
References
- CMS (Centers for Medicare and Medicaid Services): cms.gov.
- American Medical Association, CPT code overview: ama-assn.org/practice-management/cpt.
- HHS, federal No Surprises Act resources: cms.gov/nosurprises.
- Patient Advocate Foundation, billing resources: patientadvocate.org.
- Anthropic, Claude model and API documentation: docs.anthropic.com.
- Related guides on this site: blog, codes explained, extraction stats.