> ## Documentation Index
> Fetch the complete documentation index at: https://docs-apexspriteai.reliatrack.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Route Claude Code CLI to your local LM Studio backend

> Configure the Claude Code CLI to use your local LM Studio backend instead of Anthropic's cloud API. Includes config file setup and verification steps.

By default, the Claude Code CLI authenticates with Anthropic and routes every request to their cloud API. You can override this behavior with a single configuration file that points the CLI at your LM Studio server instead. Once the redirect is in place, the CLI works exactly as normal — tools, MCP integrations, and context handling all behave identically — except the model runs on your own hardware and no requests leave your network.

## Prerequisites

* Node.js 18 or later installed on your local machine
* LM Studio running on your GPU server with a model loaded and the local server started on port 1234 (see [Set up a local LLM with LM Studio](/guides/local-llm-setup))
* Network connectivity to the server: either `localhost` (same machine) or a Tailscale IP for a remote server

<Steps>
  <Step title="Install the Claude Code CLI">
    Install the official Anthropic Claude Code package globally from npm:

    ```bash theme={null}
    npm install -g @anthropic-ai/claude-code
    ```

    Confirm the installation succeeded:

    ```bash theme={null}
    claude --version
    ```
  </Step>

  <Step title="Create the Claude configuration directory">
    The CLI reads its configuration from `~/.claude/config.json`. Create the directory if it does not already exist:

    ```bash theme={null}
    mkdir -p ~/.claude
    ```
  </Step>

  <Step title="Write the config.json file">
    Create or edit `~/.claude/config.json` with the following content. Set `ANTHROPIC_BASE_URL` to the address of your LM Studio server.

    <CodeGroup>
      ```json Remote server via Tailscale (~/.claude/config.json) theme={null}
      {
        "env": {
          "ANTHROPIC_BASE_URL": "http://100.82.56.40:1234",
          "ANTHROPIC_API_KEY": "local"
        }
      }
      ```

      ```json Local server on the same machine (~/.claude/config.json) theme={null}
      {
        "env": {
          "ANTHROPIC_BASE_URL": "http://localhost:1234",
          "ANTHROPIC_API_KEY": "local"
        }
      }
      ```
    </CodeGroup>

    <Note>
      The Tailscale IP `100.82.56.40` shown above is an example. Replace it with the actual Tailscale address of your GPU server. You can find it by running `tailscale ip -4` on the server.
    </Note>

    **How this works:** Setting `ANTHROPIC_BASE_URL` redirects all API calls away from `api.anthropic.com` to your local server. The CLI never contacts Anthropic's OAuth service, so no cloud authentication occurs. The `ANTHROPIC_API_KEY` field is required by the CLI's schema but its value is not validated by LM Studio — `"local"` is a safe placeholder.
  </Step>

  <Step title="Verify the connection">
    Run a simple prompt to confirm the CLI is talking to your local model:

    ```bash theme={null}
    claude "Hello, are you running locally?"
    ```

    The model should respond. If LM Studio is the active backend, you will notice that no Anthropic sign-in prompt appears and the response originates from whichever model is loaded in LM Studio.

    <Tip>
      You can also check LM Studio's server logs in the **Developer** tab. Each request from the CLI appears as an incoming POST to `/v1/messages`, confirming the traffic is hitting your server.
    </Tip>
  </Step>

  <Step title="(Optional) Switch back to Anthropic cloud">
    To restore cloud API behavior, either delete `~/.claude/config.json` or remove the `ANTHROPIC_BASE_URL` key from the `env` object. The CLI falls back to its default Anthropic endpoint automatically.

    ```bash theme={null}
    rm ~/.claude/config.json
    ```
  </Step>
</Steps>

## Troubleshooting

<AccordionGroup>
  <Accordion title="The CLI hangs or returns a connection error">
    Confirm that LM Studio's local server is running and bound to `0.0.0.0` on port 1234. Test connectivity directly with `nc -vz <SERVER_IP> 1234`. If using Tailscale, verify both devices are connected to the same tailnet with `tailscale status`.
  </Accordion>

  <Accordion title="The CLI prompts me to sign in to Anthropic">
    This means `ANTHROPIC_BASE_URL` is not being picked up. Check that `~/.claude/config.json` is valid JSON and that the `env` key is at the top level of the object. You can validate the file with `cat ~/.claude/config.json | python3 -m json.tool`.
  </Accordion>

  <Accordion title="Responses are very slow">
    The model loaded in LM Studio may be too large for your hardware. See [Choose the right AI model](/guides/model-selection) for guidance on selecting a model that matches your server's memory capacity.
  </Accordion>
</AccordionGroup>

## Next steps

With the CLI connected to your local model, you can extend it with custom tools using the Model Context Protocol. Follow [Add MCP tools to your AI agent](/guides/adding-mcp-tools) to install and configure your first tools.