---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Set a provider for a generative AI capability

# Set a provider for a generative AI capability {#ariaid-title1}

Release version: Brazil  
Updated September 10, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Configure LLM providers for Generative AI Controller at the backend level. For most use cases, configure capabilities using AI Admin Hub.

## Before you begin

Configure your credentials for your preferred provider. See [Configuring API credentials for generative AI capabilities](https://www.servicenow.com/docs/2KZJeFz1lI07qwrRDrRIuQ "Configure the credentials and connections for your preferred generative AI service provider to integrate third-party generative AI on the ServiceNow AI Platform.") for more details.

Role required: admin

## About this task

Use this procedure to configure LLM providers at the OneExtend Capability level. Generative AI capabilities are configured using the AI Admin Hub, which is the recommended approach. This procedure is for backend configuration when you need to manage custom OneExtend configurations.

## Procedure

1. In the navigation filter, search for the OneExtend Capability table by entering <kbd class="ph userinput">sys_one_extend_capability.list</kbd>.
2. In the OneExtend Definition Configs related list, set Default to <kbd class="ph userinput">true</kbd> for your preferred capability provider.  
   Note:  
   By default, you can choose only one provider for a capability. For example, if Default is <kbd class="ph userinput">true</kbd> for Sentiment (OpenAI Completion), you must set Default to <kbd class="ph userinput">false</kbd> before changing Default to <kbd class="ph userinput">true</kbd> for Sentiment (Azure OpenAI).
   {#configure-a-provider-for-a-generative-ai-capability__entry__2}

   | Capability Definition | Model |
   |-|-|
   | * OpenAI Completion * Azure OpenAI Completion | GPT-3 |
   | * OpenAI Chat Completion * Azure OpenAI Chat Completion | GPT-3.5 |
   | * GPT4 (OpenAI Chat Compl) * GPT4 (Azure OpenAI Chat Compl) | GPT-4 |
   | * AI Studio (Google Cloud Completion) * AI Studio (Google Cloud Chat Completion) * Vertex AI (Google Cloud Completion) * Vertex AI (Google Cloud Chat Completion) | Google Gemini |
   | IBM watsonx | Granite |
   [Table 1. Model OptionsYou have the option to choose between several different models for each capability.]

## Result

The provider configuration is applied at the OneExtend Capability level and is available for use by generative AI capabilities in your instance.

## What to do next

To configure generative AI capabilities through the standard approach, see [Generative AI skills](https://www.servicenow.com/docs/tHKlq54FkdU2RwLiTObdMQ "Generative AI skills use large language models to enterprise data to complete tasks within workflows. You can activate and configure skills, or build custom skills for your organization."), [AI Skill Kit](https://www.servicenow.com/docs/rXlzROHfVxB_PPntyEiYyA "Use ServiceNow AI Skill Kit to create and publish custom prompts and skills for ServiceNow Otto. Creating custom skills and prompts gives you greater flexibility with ServiceNow Otto's generative AI capabilities."), and [AI Admin Hub](https://www.servicenow.com/docs/DXIiljicT2y3QrwyNpgJWQ "ServiceNow Otto uses generative AI to enhance user productivity and efficiency through conversation and proactive experiences.").