Air waybill OCR API that reads every AWB, master or house

An air waybill (AWB) is the main transport document for air freight. It is issued by the airline or by its agent, usually a freight forwarder, and serves both as a receipt for the goods and as evidence of the contract of carriage. It shows the shipper and consignee, the airports of departure and destination, the flight details, the number of pieces, the gross and chargeable weight, the dimensions, the description of the goods, the freight charges and any handling instructions. Mindee extracts these fields from paper, PDF or scanned air waybills and returns them as structured JSON, ready for your TMS, ERP or customs systems.

In air cargo, the AWB number is an 11-digit number made up of a 3-digit airline prefix, which identifies the carrier, followed by an 8-digit serial number whose last digit is a check digit. It is used to track the shipment throughout its journey. Express couriers and many e-commerce delivery companies also use the term “AWB number” for their own tracking numbers, which follow their own formats. Mindee extracts the AWB number from any air waybill or courier document, so each shipment can be tracked or matched with your records without manual data entry.

An air waybill is used for air freight, and a bill of lading is used for sea freight. The key difference is legal: a bill of lading can be negotiable and act as a document of title, which means whoever holds the original can claim the goods. An air waybill is always non-negotiable: the goods are delivered to the consignee named on the document, without the need to present an original. This is one reason air freight can be released faster at destination. Mindee processes both documents and identifies which one it is, so each shipment follows the right process.

When a freight forwarder groups several customers’ shipments into one consignment, two levels of air waybills are used. The airline issues a master air waybill (MAWB) to the forwarder for the whole consignment, and the forwarder issues a house air waybill (HAWB) to each shipper for their own goods. Forwarders must then check that the pieces and weights on all the house air waybills add up to the master, and bill each customer correctly. Mindee extracts both types of documents and identifies which is which, so these checks can be automated and discrepancies flagged before they lead to billing errors or customs delays.

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.