Integration guide
Kilo Code
Kilo Code is an open-source AI coding agent extension for VS Code that works with any OpenAI-compatible provider (BYOK mode). Point it at CrossModel and you can use the whole catalog inside VS Code.
Quickstart
1. Install Kilo Code
Search for Kilo Code in the VS Code Extensions panel, or install it from the Visual Studio Marketplace.
2. Create an API key
Sign in to the Console and create a key that starts with cm- on the API Keys page. The key is shown only once, so copy it somewhere safe.
3. Point Kilo Code at CrossModel
Click the Kilo Code icon in the VS Code sidebar, open the settings panel, and fill in:
| Field | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.crossmodel.ai/v1 |
| API Key | your cm- key |
| Model | Kilo Code fetches the available models once the URL is set |
Once you enter the base URL, Kilo Code pulls the model list from that endpoint automatically — just pick the one you want.
4. Start using it
Send a message in the Kilo Code chat panel and your requests will route through CrossModel to the model you picked.
Choosing models
Model IDs follow the vendor/short_name format, e.g. openai/gpt-5.5, anthropic/claude-sonnet-4.6, or deepseek/deepseek-v4-flash. See the full list in the model catalog.
Troubleshooting
| Symptom | What to check |
|---|---|
| Empty model list | Make sure the base URL ends with /v1 and the key starts with cm- and is valid. |
| Auth failure | Re-check the API key. It's shown only once, so create a new one in the Console if you've lost it. |
| "Model not found" | Check the model ID format; casing must match exactly. |
| Insufficient balance | Top up in the Console. |