> ## Documentation Index
> Fetch the complete documentation index at: https://learn.getodin.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Default Model Change — GPT-5.4 nano

> On June 15th, 2026, GPT-5.4 nano becomes the default system model in Odin AI Platform

<Info>
  **Effective date:** June 15th, 2026 · **Previous default:** GPT-4.1 mini · **Action required:** None, unless opting out
</Info>

## Overview

|                      |                             |
| -------------------- | --------------------------- |
| **Change**           | Default system model update |
| **New default**      | GPT-5.4 nano                |
| **Previous default** | GPT-4.1 mini                |
| **Effective date**   | June 15, 2026               |
| **Action required**  | None, unless opting out     |

On June 15th, 2026, **GPT-5.4 nano** becomes the default system model in Odin AI Platform. This change provides a more capable, cost-efficient, and future-ready foundation for all AI-powered workflows and agents.

## What's improving

<CardGroup cols={2}>
  <Card title="Newer model generation" icon="microchip-ai">
    GPT-5.4 nano is part of the latest model family, designed for stronger reasoning and more reliable outputs.
  </Card>

  <Card title="Increased output capacity" icon="expand">
    Supports significantly larger responses, enabling more detailed workflows, plans, and results.
  </Card>

  <Card title="Improved tool usage and reasoning" icon="screwdriver-wrench">
    Better at multi-step thinking, tool selection, and orchestrating complex agent tasks.
  </Card>

  <Card title="More recent training data" icon="database">
    Updated knowledge base leads to better accuracy across modern use cases.
  </Card>
</CardGroup>

## Cost impact

GPT-5.4 nano is more cost-efficient for most workloads. Some tasks may generate longer outputs due to improved reasoning, but the overall expected impact is **equal or lower cost per execution**.

| Factor            | Impact                         |
| ----------------- | ------------------------------ |
| Cost per token    | Lower than GPT-4.1 mini        |
| Output length     | May increase for complex tasks |
| Expected net cost | Equal or lower per execution   |

## Important: opting out

If you have workflows or agents that rely on **GPT-4.1 mini** and do not want them to migrate to the new default, you need to explicitly configure them before June 15th, 2026.

<Warning>
  If no action is taken before June 15th, 2026, all agents and workflows using the system default will automatically switch to GPT-5.4 nano.
</Warning>

<Steps>
  <Step title="Create a dedicated agent">
    Set up an agent specifically for the workflows that need to retain the previous model.
  </Step>

  <Step title="Set the model to GPT-4.1 mini">
    In the agent's **General** tab, set the model to **GPT-4.1 mini** explicitly. This overrides the system default and ensures consistent behavior for existing implementations.
  </Step>
</Steps>

## Model configuration options

You can control model usage at multiple levels:

* **Agent level** — Set a specific model in the agent's General tab. This overrides the system default for all workflows using that agent.
* **Workflow level** — Override the model for a specific workflow where required.

For instructions on setting a model at the agent level, see [Predefined and Custom Models](/agents/models).

## Summary

<CardGroup cols={2}>
  <Card title="What's better" icon="circle-check">
    * Better intelligence
    * Stronger agent capabilities
    * Larger outputs
    * Lower cost
  </Card>

  <Card title="What you need to do" icon="circle-info">
    Nothing — unless you want to keep using GPT-4.1 mini. In that case, set the model explicitly at the agent level before **June 15th, 2026**.
  </Card>
</CardGroup>

## Support

For questions about this change or help configuring your agents, contact your Odin AI account manager or open a support ticket through the [Odin AI support portal](https://apeople.automationanywhere.com/).

<Card title="Default Model Changelog" icon="clock-rotate-left" href="/agents/default-model-changelog">
  View the full history of default model changes in Odin AI Platform.
</Card>