Shipping label OCR API that reads every parcel, barcode and address

A shipping label identifies a package and tells the carrier where and how to deliver it. It usually shows the sender’s and recipient’s names and addresses, the carrier and service level (for example, express or ground), the tracking number and its barcode, the package weight, the ship date, and routing codes used to sort the package. Business shipments often add a reference such as an order or purchase order number. Mindee extracts these fields from a photo or a scan of the label and returns them as structured JSON, ready for your warehouse, mailroom or logistics systems.

It depends on the carrier. The tracking number is usually printed near the main barcode, but its format varies: UPS numbers typically start with “1Z” and contain 18 characters, FedEx numbers are often 12 digits and labeled “TRK#”, and USPS numbers are usually 20 to 22 digits, printed under “USPS TRACKING #”. Mindee extracts the tracking number whatever the carrier and also identifies the carrier itself, so each package can be tracked or logged automatically, without anyone having to figure out which number to copy.

Instead of typing each package into a log by hand, staff take a photo of the label with a phone or a fixed camera. Mindee extracts the recipient, carrier, tracking number and any order reference, and the package is logged in seconds. The recipient or the relevant team can then be notified automatically, by email or Slack, and the package routed to the right location. Labels are often creased, partly covered by tape or stuck on curved surfaces, so each field comes with a confidence score, and unclear labels are flagged for a quick manual check.

Yes. When returned packages arrive at the warehouse, the label is often the only quick way to identify them. Mindee extracts the tracking number, the sender’s name and address, and any order or return (RMA) reference printed on the label. Your system can then match each package with the right return request, trigger the inspection and refund process, and update the customer immediately. This shortens refund times and reduces the number of unidentified packages that pile up in the returns area.

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.