- Overview
- Getting started
- Building models
- Consuming models
- ML packages
- 1040 - ML package
- 1040 Schedule C - ML package
- 1040 Schedule D - ML package
- 1040 Schedule E - ML package
- 1040x - ML package
- 3949a - ML package
- 4506T - ML package
- 941x - ML package
- 9465 - ML package
- ACORD125 - ML package
- ACORD126 - ML package
- ACORD131 - ML package
- ACORD140 - ML package
- ACORD25 - ML package
- Bank Statements - ML package
- Bills Of Lading - ML package
- Certificate of Incorporation - ML package
- Certificate of Origin - ML package
- Checks - ML package
- Children Product Certificate - ML package
- CMS 1500 - ML package
- EU Declaration of Conformity - ML package
- Financial Statements - ML package
- FM1003 - ML package
- I9 - ML package
- ID Cards - ML package
- Invoices - ML package
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices Hebrew - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Invoices Shipping - ML package
- Packing Lists - ML package
- Payslips - ML package
- Passports - ML package
- Purchase Orders - ML package
- Receipts - ML Package
- Remittance Advices - ML package
- UB04 - ML package
- Utility Bills - ML package
- Vehicle Titles - ML package
- W2 - ML package
- W9 - ML package
- Public endpoints
- Supported languages
- Insights dashboards
- Data and security
- Licensing
- API Key
- Cloud and on-premises usage
- Metering and charging logic
- How to
Metering and charging logic
When using UiPath® Document UnderstandingTM modern projects, it's essential to understand the system we use for metering and charging, specifically in relation to AI units. The main operation that we charge is digitization, without charging subsequent operations, like extraction or classification. If digitization for the same document takes place multiple times, it will be charged multiple times.
- For licensing information for classic projects, check the Metering and charging logic page from the Document Understanding User Guide for classic projects.
- To track your AI units consumption at organization and tenant level, check the AI units consumption overview dashboard pages.
- To track AI units consumption for Document Understanding and AI Center projects, check the [Preview] Document Understanding and AI Center consumption dashboard page.
A unique feature for modern projects is that regardless of the operations performed on a page - be it digitization, extraction, or classification - only one single AI unit is charged. This applies to all operations, encompassing both robotic process automation (RPA) and public APIs operations.
- OCR only → 1 AI unit / page
- OCR and classification → 1 AI unit / page
- OCR, classification, and extraction → 1 AI unit / page
- OCR, classification, extraction, and Generative Validation → 2 AI units / page
- If you use the Classify Document activity to process a document, triggering digitization and the result is stored in a Document Data → 1 AI unit / input page
- If you then use the Extract Document Data activity
to:
- Process a document
using the file itself as input, triggering digitization → the total
cost is 2 AI units / page
Note: You can also process a document using the file itself with the Extract Document Data activity without classifying it previously. In this case, the total cost is 1 AI unit / page.
- Process a document using Document Data, the output of Classify Document, as input → the total cost is 1 AI Unit / page
- Process a document
using the file itself as input, triggering digitization → the total
cost is 2 AI units / page
For the InteligentOCR.Activities package, one AI unit is charged per page, regardless of the operations performed - whether it's digitization, extraction, or classification. This only applies when a modern project classifier or extractor is in use. If you use any other classifier or extractor, the respective consumption logic from the classic projects is added to the one AI unit per page. For more information, check the Mixed use section below.
There are no AI units charged when training and serving models. This means you can freely train models to improve performance, develop new capabilities, and experiment without concerns about incurring additional AI units charges.
If a project is using both classic and modern experience, both pricing models will apply based on their respective consumption.
- Extraction and classification done using public endpoints, regardless of the activity package used (IntelligentOCR or Document Understanding).
- Extraction and classification done using Generative Extraction or Generative Classification, regardless of the activity package used.
For example, if you are using Generative Classifier and extract data using a modern project, processing a five-page document, the consumption amounts to six AI units, five corresponding to the modern project, and one to the Generative Classifier.
For more information on the metering and charging logic applicable for classic scenarios, check the Document Understanding User Guide for Classic Experience.
