Edit

Share via

Document Intelligence payStub model

The Document Intelligence payStub model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract compensation and earnings data from pay slips. The API analyzes documents and files with payroll related information; extracts key information and returns a structured JSON data representation.

Feature version Model ID
payStub model v4.0: 2024-11-30 (GA) prebuilt-payStub.us

Try payStub data extraction

Pay stubs are essential documents issued by employers to employees, providing earnings, deductions, and net pay information for a specific pay period. See how data is extracted using prebuilt-payStub.us model. You need the following resources:

  • An Azure subscription—you can create one for free

  • A Document Intelligence 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.

    Screenshot of keys and endpoint ___location in the Azure portal.

Document Intelligence Studio

  1. On the Document Intelligence Studio home page, select payStub.

  2. You can analyze the sample pay stub or upload your own files.

  3. Select the Run analysis button and, if necessary, configure the Analyze options :

Input requirements

The following file formats are supported.

Model PDF Image:
JPEG/JPG, PNG, BMP, TIFF, HEIF		 Office:
Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML
Read ✔ ✔ ✔
Layout ✔ ✔ ✔
General document ✔ ✔
Prebuilt ✔ ✔
Custom extraction ✔ ✔
Custom classification ✔ ✔ ✔
  • Photos and scans: For best results, provide one clear photo or high-quality scan per document.
  • PDFs and TIFFs: For PDFs and TIFFs, up to 2,000 pages can be processed. (With a free-tier subscription, only the first two pages are processed.)
  • File size: The file size for analyzing documents is 500 MB for the paid (S0) tier and 4 MB for the free (F0) tier.
  • Image dimensions: The dimensions must be between 50 pixels x 50 pixels and 10,000 pixels x 10,000 pixels.
  • Password locks: If your PDFs are password-locked, you must remove the lock before submission.
  • Text height: 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.
  • 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.
  • Custom extraction model training: The total size of training data is 50 MB for template model and 1 GB for the neural model.
  • Custom classification model training: The total size of training data is 1 GB with a maximum of 10,000 pages. For 2024-11-30 (GA), the total size of training data is 2 GB with a maximum of 10,000 pages.
  • Office file types (DOCX, XLSX, PPTX): The maximum string length limit is 8 million characters.

Supported languages and locales

For a complete list of supported languages, see our prebuilt model language support page.

Field extractions

For supported document extraction fields, see the payStub model schema page in our GitHub sample repository.

Supported locales

The prebuilt-payStub.us version supports the en-us locale.

Next steps