Home / Integrations / Cline

Use Cline with TurboLLM

Cline is a VS Code agent that can read, edit, and run code in your editor. Point it at your local TurboLLM server through the OpenAI Compatible provider and Cline runs entirely on your own GPU — no cloud API, no per-token bill.

Connect Cline to TurboLLM

Open Cline's settings panel in VS Code and configure it as an OpenAI Compatible provider.

  1. Set the API Provider

    In Cline's settings, set API Provider to OpenAI Compatible.

  2. Set the Base URL

    Enter your local TurboLLM endpoint:

    http://localhost:6996/v1

  3. Add your API key

    Paste your TurboLLM API key. Grab one from Developer → API Keys. This is only required if Require API key is turned on — if it's off, any value (or a placeholder) works.

  4. Set a model ID

    Enter a model ID such as local. TurboLLM fuzzy-matches the ID against your loaded model, so you don't need the exact filename.

  5. Verify the connection

    Click Verify to confirm Cline can reach TurboLLM. Once it succeeds, you're ready to code.

Where these values come from

The API key lives under Developer → API Keys in TurboLLM. The Base URL points at your local server on port 6996.

Recommended models

Cline is an agentic coding tool, so pair it with a capable coder model. See the coder picks in the model catalog for models that work well for editing and running code locally.

Previous← Continue