Chatbox Integration Guide

Applicable roles: Developer, Admin User, Member User Last updated: 2026-08-06

Chatbox allows you to add custom models through the OpenAI API type. When configuring, distinguish between the API domain and the model name: the former determines where requests are sent, and the latter determines which model the platform routes to.

Adding a Connection

Open Settings and go to the model Provider section. Select OpenAI API, then add a custom model. The screenshots below are from the actual Chatbox interface; the Provider and model names have been replaced with platform configuration values.

Fill in the connection information as follows:

Field	Value
API Domain	https://<your-api-endpoint>
API Key	Your platform API Key
Custom Model Name	The model call name shown in the console "Call Guide"

Use the endpoint address shown on the "API Key" page in the console.

After saving, return to the chat window, select the newly added model, and send a short message.

Troubleshooting Duplicate Addresses

The API Domain should always be https://<your-api-endpoint>. The client should automatically append the request path based on the selected protocol. If you encounter duplicate paths, check whether you accidentally entered the full endpoint.

A successful connection should satisfy both conditions: Chatbox receives a reply, and the corresponding Key and model appear in the console usage records. If you only see a local error with no records in the console, the request has likely not reached the platform.