Passport OCR API that reads the MRZ and every visual field

The MRZ (Machine Readable Zone) is the block of two lines of characters at the bottom of a passport’s photo page. Defined by the ICAO international standard, it encodes the holder’s key details in a format machines can read: document type, issuing country, name, passport number, nationality, date of birth, sex and expiry date, plus check digits that detect reading errors. Mindee reads both the MRZ and the printed fields on the page (the visual zone) and returns them as structured JSON. You can then compare the two sources to catch inconsistencies or typing errors.

Yes. Passports from all countries follow the same ICAO format for the photo page and the MRZ, so Mindee can extract data from passports worldwide, whatever the language or alphabet of the printed fields. The MRZ always uses Latin characters, which means names are returned in a consistent, searchable format even when the visual zone is written in Cyrillic, Arabic or Asian scripts.

Mindee focuses on data extraction. It turns a passport image into accurate, structured data in seconds, but it doesn’t perform forgery detection, chip (NFC) reading or liveness checks. In a KYC or onboarding flow, Mindee typically handles the step where data is captured and pre-filled, and works alongside a dedicated identity verification provider. Confidence scores and consistency between the MRZ and the printed fields also help you flag suspicious or poor-quality captures for manual review.

A passport contains highly sensitive personal data, so where it is processed matters. Sending passport photos to a general-purpose AI chatbot can mean your data is stored or used under terms you don’t control. Mindee is built for identity document processing: it is SOC 2 Type II certified and GDPR compliant, data is encrypted in transit and at rest, and you control how long documents are retained. You also get consistent, structured output with confidence scores, instead of free-text answers that might guess a passport number or a date.

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.