How to set up Cherry Studio with Ozeki AI Gateway
This guide walks you through installing Cherry Studio 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 desktop application, add Ozeki AI Gateway using the OpenAI Compatible provider type, and verify the connection by sending a test prompt.
What is Cherry Studio?
Cherry Studio is a free, open-source desktop AI client available for Windows, macOS, and Linux. It acts as a unified interface for a wide range of large language model providers, including OpenAI, Anthropic, and locally hosted models, all accessible from a single application window. Because it supports OpenAI-compatible API endpoints, it can be connected to Ozeki AI Gateway, allowing you to route all AI requests through your own gateway.
Cherry Studio provider configuration
Provider Name: Ozeki AI Gateway
Base URL: http://{address}/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.
- Download and install Cherry Studio
- Add Ozeki AI Gateway as a model provider
- Set the configured model as default
- Test AI connection
Video tutorial
The following video shows how to download and install Cherry Studio on Windows step-by-step. The video covers running the installer, completing the setup wizard, and launching the application for the first time.
Step 1 - Download and install Cherry Studio
Open your browser and navigate to cherry-ai.com. On the homepage, click the download button for Windows to save the installer file to your machine (Figure 1).
Once the download has finished, locate the installer file in your Downloads folder and double-click it to launch the setup process (Figure 2). to proceed.
Choose whether to install the application 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.
Confirm or change the destination folder where Cherry Studio will be installed (Figure 4). The default location is recommended for most users. Click Install to begin copying the application files to your machine.
When the installation is complete, the wizard will show a confirmation screen. Click Finish to close the setup wizard and launch Cherry Studio (Figure 5). The application will open automatically so you can proceed with the initial configuration.
On the first launch, an initial setup wizard will appear offering to configure built-in providers such as OpenAI or Anthropic. Click Skip to bypass this step for now (Figure 6). You will add Ozeki AI Gateway as a custom provider manually in the next step.
Cherry Studio will open its main homepage, showing the chat interface and the sidebar with access to assistants, knowledge bases, and settings (Figure 7).
Step 2 - Add Ozeki AI Gateway as a model provider
The following video shows how to configure Cherry Studio to work with Ozeki AI Gateway step-by-step. The video covers adding a custom provider, fetching the model list, setting the default model, and testing the connection with a sample prompt.
Open the settings by clicking the gear icon in the top right corner, then navigate to Model Provider and click Add to create a new provider entry (Figure 8). This is where you define the connection details used to communicate with Ozeki AI Gateway.
Enter a recognisable name for the provider and set the provider type to OpenAI Compatible (Figure 9).
Enter the Ozeki AI Gateway base URL and API key using the values below, then click
Fetch model list to retrieve the list of models available through your gateway (Figure 10).
Replace ozkey-abc123 with the API key you created in
Ozeki AI Gateway, and replace {address} with the IP address of
your Ozeki AI Gateway installation.
Base URL: http://{address}/v1
API Key: ozkey-abc123
You will see a list with the available models. Select the model you want to use to add it to your provider (Figure 11).
Step 3 - Set the configured model as default
In the settings sidebar, navigate to the Default Model menu (Figure 12). This section allows you to specify which model Cherry Studio will use automatically when you open a new chat, so you do not have to select it manually each time.
Set the model you configured as the Default Assistant Model, Quick Model and Translate Model (Figure 13). Once saved, Cherry Studio will automatically use this model for all new conversations unless you override it in the chat view.
Step 4 - Test AI connection
Return to the main chat interface and type a test question in the input field, then press Enter or click the send button to submit the prompt (Figure 14). The request will be forwarded to Ozeki AI Gateway, which will route it to the selected model and stream the response back to the interface.
The AI response will appear in the chat window, confirming that Cherry Studio is successfully connected to Ozeki AI Gateway and routing requests through your configured model (Figure 15).
Summary
You have successfully installed Cherry Studio and configured it to use Ozeki AI Gateway as its model provider. All prompts sent from the interface are now routed through your gateway, giving you centralised control over API access, model selection, and usage monitoring.