Use Cline with the Gateway¶
Cline is an AI coding assistant that runs inside VS Code. Connect it to the Gateway to use Claude and other models through your regional endpoint, with your data staying in your chosen geography.
Prerequisites¶
- Cline installed in VS Code
- An LLM API key
Connect Cline to the Gateway¶
- Open VS Code and click the Cline icon in the sidebar
- Click the settings gear icon at the top of the Cline panel
- Under API Provider, select OpenAI Compatible
- Set the fields:
| Field | Value |
|---|---|
| Base URL | https://llm.[your-region].amazee.ai/v1 |
| API Key | Your LLM API key |
| Model ID | Pick from the list, or type an ID from Available Models (e.g. claude-4-5-sonnet) |
- In the model settings, set Context Window Size to the model's context window (e.g.
200000for Claude Sonnet). Turn on image support if the model has vision. - Click Done. Cline saves settings as you type.
Verify¶
Start a new Cline chat and ask a simple question. Check the My usage card on the AI keys page to confirm requests are flowing through your regional endpoint.
Troubleshooting¶
- "Invalid API key" or auth errors
- Double-check your API key and make sure the base URL includes
/v1at the end. - Model not found
- Once your Base URL and key are set, Cline loads the model list from the Gateway. If the list is empty, check both. Otherwise pick the model from the list rather than typing it.
- Slow responses or cut-off context
- Make sure Context Window Size matches the model. For long tasks, try a faster model, or split the task into smaller steps.