How to Integrate OneHop AI Gateway with Cline in VS Code

Integrating the OneHop AI Gateway with Cline in Visual Studio Code allows developers to manage multiple AI models more efficiently. This guide will walk you through the process step-by-step.

First, ensure you have Visual Studio Code installed, an active OneHop account with permission to create API keys, the Cline VS Code extension, and a supported model from OneHop.

Begin by installing the Cline extension in Visual Studio Code. Open the Extensions Marketplace by pressing Ctrl + Shift + X (Cmd + Shift + X on macOS) and search for "CLINE." Locate the official Cline extension published by Autonomous Coding Agent and click "Install." After installation, verify that the extension is installed and enabled in VS Code.

Next, create an API key in your OneHop account. Log in, navigate to the API Keys section, and create a new key. Copy the secret value of the key, keeping in mind that it should be stored securely, never published publicly, and treated like a password.

Now, configure the OneHop Gateway in Cline. Open the Cline settings in VS Code and select "OpenAI Compatible" as the API Provider. Enter the following configuration values:

- Base URL: https://api.onehop.ai/v1

- API Key: (your copied OneHop API key)

- Model ID: (your supported OneHop model)

The Base URL should be exactly https://api.onehop.ai/v1. The Model ID should match the exact model identifier currently supported by your OneHop account.

Finally, test the integration with a simple coding task. Ask Cline to create a TypeScript function that reverses a string. If the connection is successful, Cline should respond accordingly. For a more comprehensive test, have Cline inspect a project structure to identify the framework used, the main entry point, and the file where you should add a new API route.

If you encounter any issues, check the Base URL, API Key, and Model ID for accuracy. Ensure the API key is correct, active, and complete. Verify that the model identifier matches the exact one provided by OneHop. If the gateway is reachable but the model request fails, confirm the model's availability in your OneHop account, check account permissions, and ensure the model ID is correct.