Skip to content
mcp/harbor
Gemini CLI

LiteLLM Multi-Model API for Gemini CLI

io.github.berriai/litellm-mcp

Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.

client:Gemini CLI transport:stdio runtime:pypi

Install LiteLLM Multi-Model API in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "litellm-mcp": {
      "command": "uvx",
      "args": [
        "litellm-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "LITELLM_API_BASE": "<LITELLM_API_BASE>",
        "LITELLM_API_KEY": "<LITELLM_API_KEY>"
      }
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

LiteLLM Multi-Model API in other clients

LiteLLM Multi-Model API MCP server