Credit note OCR API that links every credit to its invoice

A credit note, called a credit memo in the US, is a document issued by a seller to reduce or cancel the amount a customer owes on an invoice. It is issued after returned goods, a pricing or billing error, a damaged delivery or a discount granted after invoicing. A credit note usually references the original invoice and shows the amount credited, including the tax adjustment (VAT, GST or sales tax). Mindee extracts the supplier and customer details, the credit note number and date, the referenced invoice number, the line items and the credited amounts, and returns them as structured JSON.

A credit note reduces the amount owed: the seller issues it to the buyer, for example after a return or an overcharge. A debit note works the other way. It is typically issued by the buyer to request a credit from the seller, for example after returning goods, or in some cases by the seller to increase the amount due after an undercharge. For example, if a customer returns $500 of goods, the buyer may send a debit note to the supplier, who then issues a $500 credit note. Mindee identifies the type of document and extracts its amounts, so each document is recorded correctly in your accounts.

Yes. Credit notes often look very similar to invoices, with the same supplier, layout and logo, and the difference sometimes comes down to a title or a minus sign. If an AP workflow mistakes a credit note for an invoice, the supplier ends up being paid instead of being credited. Mindee automatically identifies credit notes, even when they arrive in the same email inbox or file as invoices, and returns the amounts with the correct sign. Your AP team can then route them to the right workflow and record them correctly.

Most credit notes reference the invoice they correct, usually by its invoice number. Mindee extracts this reference along with the supplier, amounts and line items, so you can automatically find the original invoice in your ERP or accounting software, such as QuickBooks, Xero or Sage, and apply the credit to it. If the invoice is still unpaid, you pay only the net amount. If it has already been paid, the credit is deducted from the next payment or recorded as a refund to request. Credit notes that don’t reference an invoice, or reference one that can’t be found, are flagged for review instead of being forgotten.

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.