Tax return OCR API that reads income, tax and refund

Form 1040 is the standard US individual income tax return filed with the IRS. It reports the taxpayer’s filing status and dependents, all sources of income (wages, interest, dividends, business income, capital gains, retirement distributions), adjustments, the adjusted gross income, deductions, taxable income, the tax owed, payments already made, and the resulting refund or balance due. Depending on the taxpayer’s situation, it comes with schedules such as Schedule C for self-employment income or Schedule E for rental income. Mindee extracts the key figures from Form 1040 and returns them as structured JSON, so they can be used directly in lending, accounting or financial planning workflows.

The adjusted gross income (AGI) is your total income minus certain adjustments, such as contributions to some retirement accounts, student loan interest or half of self-employment tax. On recent versions of Form 1040, it appears on line 11, but the line number has changed over the years. AGI is one of the most widely used figures on a tax return: lenders use it to assess income, and it determines eligibility for many tax credits and benefits. Mindee extracts the AGI as a dedicated field, whatever the tax year or the layout of the form, so you don’t need to know which line to look at.

Self-employed borrowers don’t have pay stubs, so lenders usually ask for their personal tax returns for the last one or two years, with the relevant schedules (such as Schedule C for sole proprietors, or K-1s for partners and S-corporation shareholders). Underwriters then analyze the net business income, add back certain non-cash expenses such as depreciation, and often average the income over two years, paying attention to any decline. Mindee extracts these figures from each return and schedule, so the income calculation can be prepared automatically, instead of being retyped from dozens of pages for each application.

A tax return is the complete document the taxpayer filed, with all its forms and schedules. A tax transcript is a summary of that return issued by the IRS, showing the key figures the IRS has on record. Lenders often obtain the transcript directly from the IRS, with the borrower’s consent, and compare it with the return the borrower provided, to confirm that the figures match and that the return hasn’t been altered. With Mindee, the key figures from both documents can be extracted and compared automatically, and any difference is flagged for review.

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.