- Información general
- Primeros pasos
- Building Models
- Consuming Models
- Paquetes ML
- 1040: paquete ML
- 1040 Anexo C - Paquete ML
- 1040 Anexo D - Paquete ML
- 1040 Anexo E - Paquete ML
- 4506T: paquete ML
- 990 - Paquete ML: vista previa
- ACORD125: paquete ML
- ACORD126 - Paquete ML
- ACORD131 - Paquete ML
- ACORD140 - Paquete ML
- ACORD25 - Paquete ML
- Extractos bancarios: paquete ML
- Conocimientos de embarque: paquete ML
- Certificado de incorporación - Paquete ML
- Certificado de origen - Paquete ML
- Cheques: paquete ML
- Certificado de producto secundario - Paquete ML
- CMS 1500: paquete ML
- Declaración de conformidad UE - Paquete ML
- Estados financieros: paquete ML
- FM1003: paquete ML
- I9 - Paquete ML
- Documentos de identidad: paquete ML
- Facturas: paquete ML
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Envío de facturas - Paquete ML
- Listas de embalaje: paquete ML
- Recibos de pago: paquete ML
- Pasaportes: paquete ML
- Órdenes de compra: paquete ML
- Recibos: paquete ML
- ConsejosDeRemesas: paquete ML
- UB04 - Paquete ML
- Facturas de servicios públicos: paquete ML
- Títulos de vehículos: paquete ML
- W2 - Paquete ML
- W9 - Paquete ML
- Puntos finales públicos
- Idiomas admitidos
- Datos y seguridad
- Licencia
- Clave API
- Uso local y en la nube
- Lógica de medición y carga
Lógica de medición y carga
When using UiPath Document Understanding 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.
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
- One document processed using the Extract Document Data activity → 1 AI unit / input page
- One document processed with both Classify Document and Extract Document Data (same file as input) activities → 2 AI units / page
- One document processed with Classify Document (Document Data as input for the latter activity) and Extract Document Data activities → 1 AI Unit / page
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.
For example, if you are using Intelligent Keyword Classifier with a model trained using a modern project, the classic metering and charging logic will be applied for Intelligent Keyword Classifier. The model trained using the modern will follow the modern metering and charging logic described in this page.
For more information on the metering and charging logic applicable for classic scenarios, check the Document Understanding User Guide for Classic Experience.
