How to set up Chatbox with Ozeki AI Gateway

This guide walks you through installing Chatbox on Windows and connecting it to Ozeki AI Gateway as a custom model provider. By following this tutorial, you will learn how to download and install the Chatbox desktop application, add Ozeki AI Gateway using the OpenAI Compatible API mode, and verify the connection by selecting a model and sending a test prompt.

What is Chatbox?

Chatbox is a free, open-source desktop AI client available for Windows, macOS, and Linux. It provides a clean, user-friendly interface for interacting with a wide range of large language models, including those from OpenAI, Anthropic, Google, and locally hosted providers such as Ollama.

Chatbox and Ozeki AI Gateway overview
Overview

Chatbox provider configuration

Name:     Ozeki AI Gateway
API Mode: OpenAI Compatible
API Host: http://localhost/v1
API Key:  ozkey-abc123

Steps to follow

We assume Ozeki AI Gateway is already installed on your system. You can install it on Linux, Windows or Mac.

  1. Download and install Chatbox
  2. Add Ozeki AI Gateway as a model provider
  3. Select a model and send a test prompt

Video tutorial

The following video shows how to install Chatbox and configure it to work with Ozeki AI Gateway step-by-step.

Step 1 - Download and install Chatbox

Open your browser and navigate to chatboxai.app. On the homepage, click the download button for Windows to save the installer file to your machine (Figure 1).

Download the Chatbox installer from the website
Figure 1 - Download the Chatbox installer from the website

Once the download has finished, locate the installer file in your Downloads folder and double-click it to launch the setup process (Figure 2).

Run the Chatbox installer
Figure 2 - Run the Chatbox installer

Choose whether to install Chatbox for all users on the machine or only for your current account (Figure 3). If you are the only person using this computer, selecting Only for me is the simplest option. Click Next to continue.

Choose for which users to install Chatbox
Figure 3 - Choose for which users to install Chatbox

Confirm or change the destination folder where Chatbox will be installed (Figure 4). The default location is recommended for most users. Click Install to begin copying the application files to your machine.

Select the installation location
Figure 4 - Select the installation location

When the installation is complete, the wizard will show a confirmation screen. Click Finish to close the setup wizard and launch Chatbox (Figure 5). The application will open automatically so you can proceed with the provider configuration.

Press Finish to exit setup and launch Chatbox
Figure 5 - Press Finish to exit setup and launch Chatbox

Step 2 - Add Ozeki AI Gateway as a model provider

Once Chatbox is open, navigate to the settings by clicking the gear icon or the Settings button in the bottom left corner of the application (Figure 6). This will open the settings panel where you can manage model providers and other configuration options.

Navigate to Chatbox settings
Figure 6 - Navigate to Chatbox settings

In the settings panel, select Model Provider from the sidebar to see the list of configured providers (Figure 7). Click the Add button to open the form where you can enter the connection details for Ozeki AI Gateway.

Select Model Provider and click Add
Figure 7 - Select Model Provider and click Add

Enter a recognisable name for the provider and set the API Mode to OpenAI Compatible (Figure 8). This mode allows Chatbox to communicate with any API that follows the OpenAI format.

Enter provider name and select API mode
Figure 8 - Enter the provider name and select OpenAI Compatible as the API mode

Enter the AI Gateway API host URL and API key using the values below, then click Fetch to retrieve the list of models available through your gateway (Figure 9). Replace ozkey-abc123 with the API key you created in Ozeki AI Gateway. 

API Host: http://localhost/v1
API Key:  ozkey-abc123

Configure API key, host URL and fetch models
Figure 9 - Configure the API host URL and API key, then fetch models

Select the model you want to use as the default for this provider (Figure 10).

Select a model from the fetched list
Figure 10 - Select a model from the fetched list

Step 3 - Select a model and send a test prompt

Return to the main chat interface and start a new conversation. Open the model selector and choose the model you configured under the Gateway provider (Figure 11).

Start a new chat and select the configured model
Figure 11 - Start a new chat and select the configured model

Type a test question in the chat input field and press Enter or click the send button to submit the prompt (Figure 12).

Send a test prompt to the AI
Figure 12 - Send a test prompt to the AI

The AI response will appear in the chat window, confirming that Chatbox is successfully connected to the Gateway and routing requests through your configured model (Figure 13).

AI response
Figure 13 - AI response

To sum it up

You have successfully installed Chatbox and configured it to use Ozeki AI Gateway as its model provider. All prompts sent from the Chatbox interface are now routed through your gateway, giving you centralised control over API access, model selection, and usage monitoring. You can add further providers or switch models at any time from the Settings → Model Provider menu.

More information