Windsurf

This tutorial walks you through configuring Windsurf to use an OpenAI-compatible API to access LLMs hosted by Kimchi. Because Windsurf does not natively support custom third-party model providers, you'll install the Roo Code extension to route requests through the Kimchi base URL.

Overview

By the end of this tutorial, you'll be able to:

Use Kimchi-hosted models like kimi-k2.7 inside Windsurf
Route AI requests from Windsurf to Kimchi through Roo Code

📘
Windsurf's native BYOK only supports Anthropic models. To use an OpenAI-compatible endpoint such as Kimchi, you need Roo Code.

Prerequisites

A Kimchi API key from app.kimchi.dev/settings
Windsurf IDE — Download from windsurf.com
Roo Code extension — Install from the Windsurf Marketplace

Configure Windsurf

Open the Roo Code panel

In Windsurf, click the Roo Code icon in the Activity Bar. If this is your first time, follow the wizard and choose Use without an account.

Configure the third-party provider

In the Roo Code Choose a model provider panel:

Choose 3rd-party Provider from the provider list.
Set API Provider to OpenAI Compatible.
Set Base URL to https://llm.kimchi.dev/openai/v1.
Set API Key to your Kimchi API key.
Select kimi-k2.7 from the model list.
Save the configuration.

Your settings should look like this:

Roo Code LLM Provider Settings — API Provider, Base URL, and API Key configured

Verify your configuration

Open the Roo Code chat panel and send a test prompt — for example, Hello. If you receive a response, the connection to Kimchi is working.

Next steps

Rate limits

Understand request and token limits by plan before building for production.

Hosted model deployment

Deploy models on your own cluster when per-token costs exceed compute costs or compliance requires it.