Within your application's Configuration tab, you will find an "LLM Providers" sub-section. When you go to this, you will find a list of all the LLM (Large Language Model) providers that can be used by your application. The first ENABLED entry is the one that will be used by the AI agents.

Signing Up For OpenAI's Platform Services

Before you can enable the use of AI agents you must sign up for an OpenAI account. The site will then use the OpenAI API directly, via your account. (Our platform is not affiliated with OpenAI. Please note our terms of service when using these AI services).

Note: You will be responsible for all API charges. You can set a budget to help manage costs. To learn about OpenAI's pricing, please click here. Keep in mind that 1 token is about 0.75 of a single word.

Signing Up

To sign up for an OpenAI account, please visit https://platform.openai.com/login. Then create a new account (via sign-up, or clicking one of the SSO buttons).

When you complete the sign-up process, it will provide you with an API key. 

This is the key that you enter into the API Key field in the LLM Providers window.

Adding an LLM Provider

As an administrator user, go to the Configuration tab in your application. Then go to the LLM Providers area (click the hamburger in the Configuration window to select this). Then click "+" to add a new LLM Provider entry.

Below we'll provide an explanation of each of the fields:

Name: The name of the entry. You can just enter OpenAI in here.

Enabled: This should be set to YES, unless you want to test a different set of models. In that case set the main one to NO and the test entry to YES.

Default Model: This is the model name that the system will use by default, if no other model names are provided. For example, gpt-5.5.

Context Size: The context window size to use with the model. This can vary based on the specific model, so please refer to OpenAI documentation before entering a value in here. This value does not have to be the maximum context size available for that model. Please note that the larger the context size used, the more expensive the conversation or agent action can become.

API Key: This is where you will enter in the secret API key that OpenAI provided you. Once entered, it cannot be retrieved as it will be obfuscated in the display form and empty in the edit form.

Lowest Model, Low Model, Medium Model, High Model, Highest Model: You can optionally provide alternative models to use for when the agent is configured to use either the Lowest, Low, Medium, High or Highest model. This allows you to select less capable, but lower-price, models for agents that usually do not need complex reasoning. If the model name is not provided, the Default Model will be used. For example, Lowest Model may be set to gpt-5.4-nano and Highest Model may be set to gpt-5.5-pro. The models do not need to be the frontier model.

End Point Override: This usually does not need to be provided unless you are using a compatible third party service. If left empty then the system will use the default end point for the responses API.

Once these fields are filled out, you can click OK to add that LLM Provider to the system. At this point the AI agents should be usable.