Kilo Code
Connect Kilo Code, the VS Code AI assistant, to LLMAI for intelligent code generation and assistance.
Model slugs in examples are illustrative. Confirm current availability in the live catalog and your account's /v1/models before use.
What This Does
Kilo Code is an AI-powered coding assistant for VS Code that helps with code generation, explanations, debugging, and refactoring. By connecting Kilo Code to LLMAI, you access a wide range of models through a single endpoint with consolidated billing.
Setup
Step 1: Install Kilo Code
- Open VS Code
- Go to the Extensions marketplace (
Cmd+Shift+XorCtrl+Shift+X) - Search for Kilo Code
- Click Install
Step 2: Open Kilo Code Settings
- Click the Kilo Code icon in the VS Code sidebar
- Click the settings icon or navigate to Configuration
- Find the Providers section
Step 3: Configure LLMAI
Set up Kilo Code with LLMAI:
| Field | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.llmai.dev/v1 |
| API Key | Your LLMAI API key |
| Model | kimi-k2.7-code or deepseek-v4-pro |
Get your API key from console.llmai.dev/keys.
Step 4: Save and Verify
- Save the configuration
- Open the Kilo Code chat panel
- Send a test message to confirm the connection
Recommended Models for Kilo Code
| Use Case | Model | Description |
|---|---|---|
| Code generation & refactoring | kimi-k2.7-code | Moonshot's code-tuned K2.7 — best for code generation |
| Code generation | deepseek-v4-pro | Best for writing and modifying code |
| Code explanations | kimi-k2.6 | Superior reasoning for complex logic |
| Large files | minimax-m3 | Extended context window |
| Quick assistance | glm-5.1 | Fast and economical |
Troubleshooting
API key rejected
- Verify the key at console.llmai.dev/keys
- Ensure no extra spaces or line breaks in the key
Model not recognized
- Select OpenAI Compatible provider type
- Use exact model slugs from the Models reference
No response from AI
- Check Base URL is
https://api.llmai.dev/v1 - Verify your balance at console.llmai.dev/billing
Slow responses
- Switch to
glm-5.1for faster responses - Check your network connection
Notes
- Kilo Code supports inline code suggestions and chat-based interactions
- All token consumption is billed to your LLMAI account
- Usage statistics appear in real-time on your LLMAI dashboard
- Consider using different models for different tasks to optimize cost and performance