AI Center user guide

Last updated May 8, 2026

DELIVERY:

Invoke public ML Skills using API

Before starting this procedure, check the following pages for more information on ML Skills:

To use a public ML Skill, you need the following:

Port 433 must be open.
Access to the target ML Skill URL.
Access to the AI Units API key for the organization the ML Skill is deployed on.

A public ML Skill generates a URL and an API key. These will be used in an API call to request predictions.

You can find the URL and the API key in the ML Skill details section.

Create a POST request with the generated ML Skill URL.
Create a X-UIPATH-License header field using the value generated by the API key.
Create a Content-Type header field with the application/json value for inputs in JSON format (or ML Skills that expect data in JSON.
Create a request body containing actual data in JSON format:
```
curl --location --request POST 'yourURL' \
--header 'X-UIPATH-License: yourAPIKey' \
--header 'Content-Type: application/json' \
--data-raw '{"data":"test"}'
curl --location --request POST 'yourURL' \
--header 'X-UIPATH-License: yourAPIKey' \
--header 'Content-Type: application/json' \
--data-raw '{"data":"test"}'
```

PREVIOUSML Skills

NEXTSave infrastructure costs using AI Center APIs