OpenAI has introduced a significant enhancement to its ChatGPT platform, allowing users to select from a variety of AI models when creating or utilizing custom GPTs. Previously, users were restricted to the GPT-4o model for custom GPTs. With this update, options now include GPT-4o, o3, o4-mini, o4-mini-high, GPT-4.5, GPT-4.1, and GPT-4.1-mini.
Understanding Custom GPTs
Custom GPTs are personalized versions of ChatGPT that integrate specific instructions, additional knowledge, and tailored skills to meet individual user needs. For instance, a user frequently seeking assistance with social media SEO can create a custom GPT that retains specific prompts, settings, behaviors, and relevant files, streamlining the process for future interactions.
Details of the Update
The recent update introduces a Recommended Model setting, providing GPT creators with a default model selection while still offering the flexibility to switch models as needed. OpenAI elaborates:
> When the user loads a new conversation with the GPT, the recommended model will be used. If the model is not available to the user, a similar model may be automatically selected.
Limitations and Availability
There are certain limitations to this new feature. Users can only switch between different models if their custom GPT does not utilize Actions such as API calls, web browsing, or code interpreter features. For GPTs that rely on these Actions, the model selection remains limited to a smaller set of supported models. OpenAI is actively working to expand this functionality in future updates.
Currently, this feature is accessible to Pro, Plus, and Team users. OpenAI has indicated that Enterprise and EDU users will receive these capabilities in upcoming releases.
Implications for Users
This enhancement marks a significant step in OpenAI’s commitment to providing users with greater control and customization over their AI interactions. By offering a range of models, users can tailor their custom GPTs more precisely to their specific requirements, potentially improving efficiency and effectiveness in various applications.
Conclusion
The ability to choose from multiple AI models when creating custom GPTs represents a notable advancement in the ChatGPT platform. While certain limitations persist, OpenAI’s ongoing efforts to expand and refine this feature demonstrate a dedication to enhancing user experience and personalization in AI interactions.
