Insurance card OCR API that reads any US health insurance card

A US health insurance card usually shows the insurer’s name and plan type (HMO, PPO, EPO…), the member’s name and member ID, the group number, and the copays for common visits. Prescription details (Rx BIN, Rx PCN and Rx Group) are used by pharmacies, and the back often lists the payer ID, the claims address and customer service phone numbers. Mindee extracts all these fields from a photo of the front and back of the card and returns them as structured JSON. Healthcare providers can then fill in patient records and insurance information without manual typing.

The member ID (sometimes called the policy number or subscriber ID) identifies the individual covered by the plan. Dependents often share the subscriber’s ID, with a different suffix. The group number identifies the plan the member belongs to, usually through their employer. Both are needed for eligibility checks and claims, and mixing them up is a common source of errors at patient intake. Mindee returns each one as a separate, clearly labeled field, whatever the insurer’s wording or card layout.

Yes. Every insurer uses its own card design and terminology, whether it’s Aetna, Blue Cross Blue Shield, Anthem, Cigna, UnitedHealthcare, or Medicaid and Medicare Advantage plans. Mindee doesn’t rely on templates, so it handles these different layouts and returns the same output structure for every card. Patients can simply take a photo of their card on their phone during online check-in, and your team receives data that is ready for eligibility verification. This reduces front-desk work and helps prevent claim denials caused by incorrect insurance information.

Health insurance cards contain protected health information (PHI), so how it is processed matters. Mindee could be HIPAA compliant and can sign a Business Associate Agreement (BAA) with covered entities and business associates. It is mainly focused on SOC 2 Type II certified, and data is encrypted in transit and at rest. You stay in control of data retention, so you can keep only the fields you need in your own systems.

Yes, your data is highly secured and protected during the entire conversion process. As an enterprise-grade OCR solution, Mindee takes data privacy very seriously. Here are the key security measures in place:

• Certified compliance: Mindee's infrastructure is SOC 2 Type II certified and fully GDPR compliant, ensuring strict industry standards for data protection.
• Encryption: All documents and extracted data are fully encrypted both in transit (during the API call) and at rest.
• Data localization: You have control over where your data is processed, with the option to host and process your data on either EU or US servers.
• Strict privacy: Mindee respects data confidentiality. Your processed documents are not shared with third parties, and your private data is not used to train global AI models.

In short, your sensitive documents are processed in a secure, isolated environment and remain completely under your control.

We provide a 14 days free trial so you can fully test any of our OCR models — no credit card required. After this, we offer different pricing tiers depending of the volume of pages processed and the features you might need. See the pricing page for more information.

The supported document formats are:

• PDF (application/pdf) – While technically a document format rather than an image, it is natively supported for all extraction models.
• JPEG / JPG (image/jpeg)
• PNG (image/png) – Must be non-animated.
• WebP (image/webp)
• TIFF / TIF (image/tiff) – Both single-page and multi-page TIFFs are supported and processed similarly to PDFs.
• HEIC (image/heic) – Apple's High-Efficiency Image Container format.

‍

📌 Important technical limitations to keep in mind:

To ensure the OCR pipeline runs smoothly and successfully returns your JSON, make sure your files adhere to the following constraints:

• Maximum file size: 100 MB per file.
• Maximum page count: Up to 200 pages per document.
• File state: The files cannot be encrypted, and PDFs must not be password-protected.