Purchase order OCR API that reads every line, from any buyer

A purchase order (PO) is a document a buyer sends to a supplier to order goods or services. It specifies what is being bought, in what quantities, at what prices and under what terms. It typically includes a unique PO number, the buyer and supplier details, the order date, the shipping and billing addresses, the line items (item reference, description, quantity, unit price) and the expected delivery date. Mindee extracts all these fields, including every line item, from a PDF, a scan or an email attachment and returns them as structured JSON, ready to be loaded into your ERP.

A purchase order is sent by the buyer before the purchase to place an order. An invoice is sent by the supplier afterwards to request payment for what was delivered. In accounts payable, the two are compared during “three-way matching”: the PO, the goods receipt and the invoice must agree on items, quantities and prices before payment is approved. Mindee extracts both purchase orders and invoices with matching line-level detail, so you can automate this check and only review the discrepancies.

Suppliers often receive purchase orders from many customers by email, in very different formats. Sales or customer service teams then retype them into the ERP to create sales orders. With Mindee, each incoming PO is sent to the API, through code or with no-code tools like Zapier, Make or n8n, and the customer details, references, quantities, prices and delivery dates come back as structured data. Orders with high confidence scores can be created automatically in the ERP, and the others are sent for quick review. This speeds up order processing and reduces entry errors that lead to wrong deliveries.

In general, a purchase order is an offer from the buyer, and it usually becomes a binding contract once the supplier accepts it, either explicitly (through an order confirmation) or by fulfilling the order. Its exact legal value depends on the jurisdiction and on the terms and conditions attached. Because POs carry commitments on prices, quantities and delivery dates, having them as structured data helps you track what was agreed and compare it with what is delivered and invoiced. For framework agreements and longer contracts, Mindee’s contract extraction can capture key terms in the same way.

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.