Form Recognizer invoice model
The invoice model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract key fields and line items from sales invoices. Invoices can be of various formats and quality including phone-captured images, scanned documents, and digital PDFs. The API analyzes invoice text; extracts key information such as customer name, billing address, due date, and amount due; and returns a structured JSON data representation. The model currently supports both English and Spanish invoices.
Sample invoice processed with Form Recognizer Studio:
The following tools are supported by Form Recognizer v3.0:
The following tools are supported by Form Recognizer v2.1:
Try Form Recognizer
See how data, including customer information, vendor details, and line items, is extracted from invoices using the Form Recognizer Studio. You'll need the following resources:
An Azure subscription—you can create one for free
A Form Recognizer instance in the Azure portal. You can use the free pricing tier (
F0) to try the service. After your resource deploys, select Go to resource to get your key and endpoint.
Form Recognizer Studio
On the Form Recognizer Studio home page, select Invoices
You can analyze the sample invoice or select the + Add button to upload your own sample.
Select the Analyze button:
For best results, provide one clear photo or high-quality scan per document.
Supported file formats:
Model Image: JPEG/JPG, PNG, BMP, and TIFF Microsoft Office: Word (DOCX), Excel (XLS), PowerPoint (PPT), and HTML Read ✔ ✔ ✱ REST API version
Layout ✔ ✔ General Document ✔ ✔ Prebuilt ✔ ✔ Custom ✔ ✔
✱ Microsoft Office files are currently not supported for other models or versions.
For PDF and TIFF, up to 2000 pages can be processed (with a free tier subscription, only the first two pages are processed).
The file size for analyzing documents must be less than 500 MB for paid (S0) tier and 4 MB for free (F0) tier.
Image dimensions must be between 50 x 50 pixels and 10,000 px x 10,000 pixels.
PDF dimensions are up to 17 x 17 inches, corresponding to Legal or A3 paper size, or smaller.
If your PDFs are password-locked, you must remove the lock before submission.
The minimum height of the text to be extracted is 12 pixels for a 1024 x 768 pixel image. This dimension corresponds to about 8-point text at 150 dots per inch (DPI).
For custom model training, the maximum number of pages for training data is 500 for the custom template model and 50,000 for the custom neural model.
For custom model training, the total size of training data is 50 MB for template model and 1G-MB for the neural model.
The Sample Labeling tool does not support the BMP file format. This is a limitation of the tool not the Form Recognizer Service.
Supported languages and locales
||English (United States)—en-US|
||Spanish (United States)—es|
|CustomerId||String||Customer reference ID|
|PurchaseOrder||String||Purchase order reference number|
|InvoiceId||String||ID for this specific invoice (often "Invoice Number")|
|InvoiceDate||Date||Date the invoice was issued||yyyy-mm-dd|
|DueDate||Date||Date payment for this invoice is due||yyyy-mm-dd|
|VendorTaxId||String||The taxpayer number associated with the vendor|
|VendorAddress||String||Vendor mailing address|
|VendorAddressRecipient||String||Name associated with the VendorAddress|
|CustomerAddress||String||Mailing address for the Customer|
|CustomerTaxId||String||The taxpayer number associated with the customer|
|CustomerAddressRecipient||String||Name associated with the CustomerAddress|
|BillingAddress||String||Explicit billing address for the customer|
|BillingAddressRecipient||String||Name associated with the BillingAddress|
|ShippingAddress||String||Explicit shipping address for the customer|
|ShippingAddressRecipient||String||Name associated with the ShippingAddress|
|PaymentTerm||String||The terms of payment for the invoice|
|SubTotal||Number||Subtotal field identified on this invoice||Integer|
|TotalTax||Number||Total tax field identified on this invoice||Integer|
|TotalVAT||Number||Total VAT field identified on this invoice||Integer|
|InvoiceTotal||Number (USD)||Total new charges associated with this invoice||Integer|
|AmountDue||Number (USD)||Total Amount Due to the vendor||Integer|
|ServiceAddress||String||Explicit service address or property address for the customer|
|ServiceAddressRecipient||String||Name associated with the ServiceAddress|
|RemittanceAddress||String||Explicit remittance or payment address for the customer|
|RemittanceAddressRecipient||String||Name associated with the RemittanceAddress|
|ServiceStartDate||Date||First date for the service period (for example, a utility bill service period)||yyyy-mm-dd|
|ServiceEndDate||Date||End date for the service period (for example, a utility bill service period)||yyyy-mm-dd|
|PreviousUnpaidBalance||Number||Explicit previously unpaid balance||Integer|
Following are the line items extracted from an invoice in the JSON output response (the output below uses this sample invoice)
|Name||Type||Description||Text (line item #1)||Value (standardized output)|
|Items||String||Full string text line of the line item||3/4/2021 A123 Consulting Services 2 hours $30.00 10% $60.00|
|Amount||Number||The amount of the line item||$60.00||100|
|Description||String||The text description for the invoice line item||Consulting service||Consulting service|
|Quantity||Number||The quantity for this invoice line item||2||2|
|UnitPrice||Number||The net or gross price (depending on the gross invoice setting of the invoice) of one unit of this item||$30.00||30|
|ProductCode||String||Product code, product number, or SKU associated with the specific line item||A123|
|Unit||String||The unit of the line item, e.g, kg, lb etc.||Hours|
|Date||Date||Date corresponding to each line item. Often it's a date the line item was shipped||3/4/2021||2021-03-04|
|Tax||Number||Tax associated with each line item. Possible values include tax amount, tax %, and tax Y/N||10%|
|VAT||Number||Stands for Value added tax. VAT is a flat tax levied on an item. Common in European countries||€20.00|
The invoice key-value pairs and line items extracted are in the
documentResults section of the JSON output.
The prebuilt invoice 2022-06-30 and later releases support returns key-value pairs at no extra cost. Key-value pairs are specific spans within the invoice that identify a label or key and its associated response or value. In an invoice, these pairs could be the label and the value the user entered for that field or telephone number. The AI model is trained to extract identifiable keys and values based on a wide variety of document types, formats, and structures.
Keys can also exist in isolation when the model detects that a key exists, with no associated value or when processing optional fields. For example, a middle name field may be left blank on a form in some instances. key-value pairs are always spans of text contained in the document. If you have documents where the same value is described in different ways, for example, a customer or a user, the associated key will be either customer or user based on context.
Form Recognizer v3.0
The Form Recognizer v3.0 introduces several new features, capabilities, and AI quality improvements to underlying technologies.
Follow our Form Recognizer v3.0 migration guide to learn how to use the v3.0 version in your applications and workflows.
Explore our REST API to learn more about the v3.0 version and new capabilities.
Complete a Form Recognizer quickstart:
Explore our REST API:
Submit and view feedback for