simonw/llm-gemini

LLM plugin to access Google's Gemini family of models

What it solves

This project provides a plugin for the llm CLI tool, enabling seamless API access to Google's Gemini family of models. It allows users to interact with these models directly from the command line, manage API keys, and leverage advanced multimodal capabilities without writing custom integration code.

How it works

The plugin integrates Gemini models into the llm ecosystem. Once installed, users configure their API key and can call various Gemini models (such as Gemini Flash or Gemma) using the -m flag. It supports multimodal inputs by allowing users to attach images, audio, video, and even YouTube URLs as context for prompts.

Who it’s for

Developers and power users who use the llm CLI tool and want to integrate Google's Gemini models into their workflows, particularly those needing multimodal analysis or server-side tools like code execution and Google Search grounding.

Highlights

  • Multimodal Support: Process images, audio, video files, and YouTube URLs as prompt attachments.
  • Server-Side Tools: Support for CodeExecution (Python sandbox), GoogleSearch (grounding), and URLContext (fetching web content).
  • Structured Output: Ability to force JSON output using the json_object option.
  • Embeddings: Support for multiple Gemini embedding models with configurable vector dimensions (768, 1536, 3072).
  • Interactive Chat: Integration with the llm chat command for conversational AI.

Related

  • Project
    jenslys/opencode-gemini-auth

    A Gemini OAuth plugin for Opencode that enables authentication via Google accounts to access Gemini plans and quotas.

  • Project
    google-gemini/gemini-cli

    An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

  • Project
    Sophomoresty/gemini-web2api

    gemini‑web2api is a Python server that proxies Google Gemini’s private web API and presents it as an OpenAI‑compatible endpoint (`/v1/chat/completions`, `/v1/models`, etc.). It supports optional API‑key auth, streaming, function calling, image input, multiple Gemini model aliases, adjustable reasoning depth, and can run directly or inside Docker.

  • Project
    googleapis/js-genai

    Official JavaScript/TypeScript SDK (`@google/genai`) for calling Gemini LLMs via the Gemini Developer API or Gemini Enterprise Agent Platform. Provides model calls, streaming, chat state, caching, file upload, live sessions, function‑calling tools, and a high‑level Interactions API for complex, multimodal workflows.

  • Project
    googleapis/go-genai

    A Go SDK that provides an interface for developers to integrate Google's Gemini generative models into their applications.