---
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


---

# LLMs

# Large language models used by Content Understanding {#ariaid-title1}

Release version: Brazil  
Updated March 12, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
The Content Understanding application uses large language models (LLMs) to support generative AI and agentic AI capabilities.

## Available LLMs {#cu-llms__section_yqt_mgj_lgc}

You can select the LLM when creating a use case. The LLM can also be selected for the AI agent to use when processing documents and images.

Multimodal LLMs support image mode by processing multiple types of inputs --- such as text, sound, and images --- to generate a text response. Processing may take longer for image inputs.  
Note:  
The Content insights AI agent requires a multimodal LLM. The text-only Now LLM Service is not supported for the AI agent.

AI-generated outputs may be inaccurate or incomplete. Review all AI-generated content before use.

The following table lists the available LLMs for Content Understanding.
{#cu-llms__table_fq5_fhj_lgc__entry__2}

| LLM | Highlights |
|-|-|
| Now LLM Service - Large | Text-only model that supports natural language understanding, automation, and decision support. |
| Now LLM Service - Small | Text-only model that enhances text-based automation and content generation in ServiceNow workflows. |
| Google Cloud - Gemini Large | Multimodal model with advanced reasoning and problem-solving capabilities. |
| Google Cloud - Gemini Small | Multimodal model with strong performance in summarization, rewriting, and content transformation. |
| Azure OpenAI - GPT Large | Multimodal model with strong performance on tasks involving analysis, summarization, and multi-step problem solving. |
| Azure OpenAI - GPT Small (default) | Multimodal model optimized for routine workflows, including summarization, paraphrasing, and question and answer tasks. |
| Amazon Bedrock - Claude Large | Multimodal model with strong context management for long documents and dialogs. |
| Amazon Bedrock - Claude Small | Multimodal model with lower latency and higher efficiency for real-time applications. |
[Table 1. LLM options for Content Understanding]

{#cu-llms__table_fq5_fhj_lgc}

For more information, see [Large language models on the ServiceNow AI Platform](https://www.servicenow.com/docs/n9Fhw_aoChK4eS_0CvJa8w "ServiceNow AI Platform utilises large language models (LLM) for generative AI and agentic AI functionality. You can choose the ServiceNow LLM or supported third-party models. LLMs bring about the Generative AI application capabilities by understanding and generating human language, and processing vast amount of data.").