Windsurf

Configure Windsurf, Codeium's AI-native IDE, to route through LLM247 for model flexibility and unified billing.

What This Does

Windsurf is an AI-native code editor built by Codeium. It features deep AI integration including Cascade, an agent that can understand your entire codebase. By connecting Windsurf to LLM247, you can use any model in the LLM247 catalog while managing costs through a single unified balance.

Setup

Step 1: Open Windsurf Settings

Launch Windsurf
Click the gear icon in the sidebar or press Cmd+, (macOS) / Ctrl+, (Windows/Linux)
Navigate to AI Providers or Cascade Settings

Step 2: Add a New Provider

Click Add Provider or + Add AI Provider
Select OpenAI Compatible from the provider list

Step 3: Configure LLM247

Enter the following configuration:

Field	Value
Provider Name	`LLM247` (or any name you prefer)
Base URL	`https://api.llm247.net/v1`
API Key	Your LLM247 API key
Model ID	`kimi-k2.6` or `deepseek-v4-pro`

Get your API key from llm247.net/keys.

Step 4: Save and Activate

Save the provider configuration
Select LLM247 as your active provider
Choose your preferred model from the model picker

Step 5: Alternative — Settings JSON

For advanced configuration, edit the settings file directly:

Open command palette: Cmd+Shift+P
Search for Open User Settings (JSON)
Add the configuration:

{
  "windsurf.aiProvider": "openai-compatible",
  "windsurf.openaiCompatibleBaseUrl": "https://api.llm247.net/v1",
  "windsurf.openaiCompatibleApiKey": "YOUR_LLM247_API_KEY",
  "windsurf.openaiCompatibleModel": "kimi-k2.6"
}

Recommended Models for Windsurf

Feature	Model	Why
Cascade (agent mode)	`kimi-k2.6`	Best for complex multi-step tasks
Code generation	`deepseek-v4-pro`	Optimized for programming
Large codebase analysis	`minimax-m3`	Extended context window
Quick chat responses	`glm-5.1`	Fast and cost-effective

Troubleshooting

Provider not appearing in list

Ensure you selected OpenAI Compatible, not plain OpenAI
Save settings and restart Windsurf

Authentication errors

Verify your API key is correct at llm247.net/keys
Re-paste the key without any extra spaces or newlines

Cascade doesn't work with LLM247

Cascade requires models with strong agentic capabilities — use kimi-k2.6 for best results
Some Cascade features may require specific model capabilities

Slow responses

Use glm-5.1 for faster responses
Check your remaining balance at llm247.net/billing

Notes

Windsurf's UI evolves frequently — exact menu paths may differ between versions
Cascade is Windsurf's flagship feature — it works best with capable models like Kimi K2.6
Token usage is logged to your LLM247 dashboard in real-time
For tab completions, consider configuring a faster model separately if Windsurf supports it

On this page