---
schema_version: "1"
id: 7111084f7450732b6e6af4f1453f65985a97f15d5174b494576f02972fe4bf83
title: Choosing an AI Model for a Subagent
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/agent_subagents_model.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.agent_subagents_model.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: ee55ea643ed66ca0939e64378818d8138960db5856f98a7502258c8326fbd669
description: Choose the right AI model for each part of your agent to balance response speed, accuracy, and reasoning depth.
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Choosing an AI Model for a Subagent

Choose the right AI model for each part of your agent to balance response speed, accuracy, and reasoning depth.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: Lightning Experience</td></tr><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: <strong>Enterprise</strong>, <strong>Performance</strong>, <strong>Unlimited</strong>, and <strong>Developer</strong> Editions. <a href="https://help.salesforce.com/s/articleView?id=ai.agent_setup_explore_types.htm&amp;release=264.0.0&amp;type=5" title="Learn about agent types and default templates for specific clouds and common use cases.">Required add-on licenses vary by agent type.</a></td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
      <colgroup>
        <col style="width:50%">
        <col style="width:50%">
      </colgroup>
      <thead class="slds-text-title_caps ">
        <tr class="">
          <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d67776e76">User Permissions
            Needed</th>
        </tr>
      </thead>
      <tbody>
        <tr class="">
          <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d67776e76 ">&nbsp;</td>

          <td class="slds-cell-wrap" style="vertical-align:top;" headers="d67776e76 ">Manage AI Agents AND <a href="https://help.salesforce.com/s/articleView?id=ai.agent_setup_explore_types.htm&amp;type=5&amp;language=en_US" target="_blank">the required permissions for your agent
              type</a></td>

        </tr>
      </tbody>
    </table>

## How Model Override Works

Use model override when a subagent's specific job benefits from a different balance of speed and reasoning depth.

When a subagent runs, Agentforce determines which model to use in this order:

1. The model set on the subagent
2. The model set for the agent
3. The model selected in Setup. By default, every agent uses the model specified on the Einstein Audit, Analytics, and Monitoring Setup page. To change the default model, see [Select Agentforce Model Option](https://help.salesforce.com/s/articleView?id=ai.agent_setup_select_model_provider.htm&release=264.0.0&type=5 "We recommend using the Salesforce Default model option for Agentforce, which enables Salesforce to select the best model mix for agent accuracy and performance. But you can choose an AWS-Hosted or Google Gemini model option instead.").

For example, let's say your default model in Setup is GPT-4.1, your agent's model isn't set, and you select Google Gemini 2.5 Flash on the General FAQ subagent. Agentforce uses Google Gemini 2.5 Flash when the General FAQ subagent runs, but it uses GPT-4.1 for all other subagents.

Model override doesn't affect the model that prompt templates in actions use.

## Choosing a Model for a Subagent

The model that a subagent uses affects how reliably it follows instructions, how fast it responds, and how well it handles complex tasks. When choosing a model, consider these factors:

- The model's context window determines how much the model can process in one session. A model with a small context window can lose track of earlier conversation turns or drop instructions in long interactions.
- Smaller models are faster but are more likely to generate inaccurate information, misinterpret complex instructions, and produce malformed structured output. They also tend to ask more clarifying questions or add small talk.
- If your subagent only processes text, a text-only model is often faster than a multimodal model.

 
| Subagent's job | Model guidance |
| --- | --- |
| Simple routing or classification | Use the HyperClassifier model, a Salesforce model optimized for subagent classification, or a similar small model. For more information, see [Subagent Classification and Routing](https://help.salesforce.com/s/articleView?id=ai.agent_topics_routing.htm&release=264.0.0&type=5 "Learn more about the Agent Router and how to customize it to control how your agent selects subagents in a conversation."). |
| Looking up records or performing simple tasks | Use a small model that reliably follows instructions and calls the right action. |
| Complex reasoning, multi-step analysis, or long-form generation | Use a large model with strong reasoning capabilities. |
| Structured output | Use a large model that handles structured output reliably. |
| Image or document processing | Use a model with multimodal support. For a list of available models, see [Large Language Model Multimodal Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_llm_multimodal_support.htm&release=264.0.0&type=5 "Salesforce-managed models have different levels of support and limits for including JPG, PNG, or PDF files in a model request."). |

For a list of available models and their capabilities, see [Supported Models](https://developer.salesforce.com/docs/einstein/genai/guide/supported-models.html). The Einstein Trust Layer applies to all model calls.

Test how the subagent performs in the Preview panel and Testing Center.

- Run the same conversations with different models and compare response quality, directness, and speed.
- Start with a capable model to set a baseline. Then try smaller models to find the smallest one that meets your business needs.
- Test edge cases. Models handle vague or incomplete messages differently.

## Considerations

- Model override is available only for agents created in the new Agentforce Builder.
- For information about model deprecation, see [Prepare for Model Deprecation and Rerouting](https://help.salesforce.com/s/articleView?id=ai.generative_ai_model_deprecation_rerouting.htm&release=264.0.0&type=5 "This document provides guidance on retesting Salesforce AI implementations during model deprecation and rerouting. Deprecation and rerouting are considered temporary. If your model is in one of these states, consider switching to a new model.")

#### See Also

- [Building Agents in Canvas View](https://help.salesforce.com/s/articleView?id=ai.agent_canvas.htm&release=264.0.0&type=5 "Get to know the features of Agentforce Builder’s Canvas view that help you build powerful and reliable agents with Agent Script.")
- [Large Language Model Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_large_language_model_support.htm&release=264.0.0&type=5 "Understand supported large language models (LLMs) from multiple providers for embedded features, such as Prompt Builder. Identify the Salesforce-managed models that are available out of the box. Learn how you can bring your own model (BYOLLM) by using AI Models (formerly Einstein Studio).")
- [Agentforce and Generative AI Usage and Billing](https://help.salesforce.com/s/articleView?id=ai.generative_ai_usage.htm&release=264.0.0&type=5 "Salesforce provides several options for how you pay for AI usage.")