In Mavibot, you can connect your own AI model to your AI Assistant — for example, ChatGPT, Claude, or another supported model.

Important! You’ll need an API key to connect your model. The key is generated in your AI provider’s account. Requests from Mavibot will be sent directly to the provider’s API and charged according to the provider’s pricing.

If you don’t specify a model name, the model shown in the settings hint will be used by default.

Below, we’ll show you how to connect your model using OpenAI (ChatGPT) as an example.

Step 1. Sign in to OpenAI Platform

Go to OpenAI Platform and sign in to your account.

Step 2. Create an API key

Open the API Keys section and click Create new secret key.

Create a new key and save it somewhere secure right away — you won’t be able to view the full API key again after it’s created.

Please note: ChatGPT Plus/Pro subscriptions and OpenAI API usage are separate services and are billed separately. You may need to set up a payment method (Billing) in OpenAI Platform to use the API.

Never share your API key with anyone or publish it publicly.

Step 3. Open AI settings in Mavibot

Go to AI settings in Mavibot and select Custom Model.

Step 4. Connect your provider

Select your AI provider. In this example, choose OpenAI (ChatGPT).

Paste the API key you created into the corresponding field.

If needed, enter the model name. If you leave this field empty, the model shown in the settings hint will be used by default.

Step 5. Save and test

Save your settings and test your AI Assistant.

Done! Your Mavibot AI Assistant will now use the AI model you connected.