<p>Depending on the ChatGPT account (free or paid) there are usage limits. If you exceed the limit, there will be an error message like this:</p>
<p><em>Error 429: Too Many Requests insufficient_quota: You exceeded your current quota, please check your plan and billing details</em></p>
<p>In this case, you’ll either need to wait, or upgrade your ChatGPT plan. Please <ahref="https://help.openai.com/en/articles/6843909-rate-limits-and-429-too-many-requests-errors">see here</a> for details.</p>
<p>Note that you are required to switch to a paid plan after the testing period.</p>
<p><br></p>
<p>You can select the <ahref="https://platform.openai.com/docs/models/overview">model</a>, configure the <ahref="https://platform.openai.com/docs/api-reference/chat/create#chat/create-temperature">temperature</a> and enable <ahref="https://platform.openai.com/docs/api-reference/moderations">moderation</a> in the integration settings.</p>
<p>If you have access to GPT-4, you can change the model name to <ahref="https://platform.openai.com/docs/models/gpt-4">gpt-4</a> in the integration settings. There is currently a <ahref="https://openai.com/waitlist/gpt-4-api">waitlist</a> for API GPT-4 access.</p>