Mortgage OCR API that turns loan files into clean data

A mortgage statement is the periodic statement, usually monthly, that a loan servicer sends to a borrower. It shows the loan number, the borrower’s name and property address, the amount due and due date, how the payment is split between principal, interest and escrow, the outstanding principal balance, the interest rate, and any past-due amounts or fees. Mindee extracts all these fields from a PDF or a scan and returns them as structured JSON. Lenders can then use them directly in refinancing, underwriting or loan servicing workflows.

The escrow balance is the money held by the servicer to pay the property taxes and homeowners insurance on the borrower’s behalf. An escrow advance means the servicer has paid more than the balance available. A curtailment is an extra payment applied directly to the principal, which reduces the loan balance faster. PMI (private mortgage insurance) is usually required on conventional loans when the down payment is below 20%, and hazard SFR refers to the hazard insurance on a single-family residence. Mindee extracts each of these amounts as separate fields, so you don’t have to interpret every servicer’s layout and terminology yourself.

A mortgage application usually requires proof of identity, proof of income (pay stubs, W-2s or tax returns), recent bank statements, proof of address and, for a refinance, the current mortgage statement. Mindee processes these documents through a single API, including payslips, bank statements, ID cards, passports, proofs of address and mortgage statements. Each document comes back as structured data with confidence scores. Lenders and brokers can then build a complete borrower file automatically, instead of re-typing data from dozens of pages for each application.

Mortgage statement data is used at several steps of the lending process. In a refinance, it provides the current balance, rate and monthly payment of the existing loan. In underwriting, the full monthly payment, including escrow, goes into the borrower’s debt-to-income ratio, and statements confirm the properties the borrower already owns. Servicers and investors also use the data when transferring or onboarding loan portfolios. With Mindee, these figures are extracted in seconds and can be compared automatically with the application and the borrower’s bank statements, where the mortgage payments appear.

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.