how to fix gemini cli proxy timeout errors

Timeout errors are usually due to network issues; configure your terminal proxy with export commands as shown in the README (e.g., export https_proxy=http://127.0.0.1:7890) before starting the service, and ensure Gemini CLI itself can connect to Google.

can I use gemini cli proxy with LangChain or LlamaIndex

Yes, since it's OpenAI-compatible, you can integrate it by setting the base_url in LangChain's OpenAI class or similar tools, just like the Python client example in the README. However, advanced features like streaming might not work.

gemini cli proxy vs official google ai api

Gemini CLI Proxy uses the free CLI tool with network dependencies and basic features, while the official Google AI API is paid, more reliable, and offers full capabilities like streaming and better rate limits. Choose based on cost vs. production needs.

how to deploy gemini cli proxy on a server

Not recommended for production, but you can run it on a server with stable proxy access; use process managers like systemd or Docker, and ensure the Gemini CLI is installed and authenticated. Monitor for network failures and timeouts.

does gemini cli proxy support streaming responses

No, the README only mentions the chat completions endpoint without streaming support; it returns full responses, so it's not suitable for real-time applications that need token-by-token output.

is gemini cli proxy free for commercial use

The proxy itself is MIT-licensed, but it relies on Google's Gemini CLI, which may have usage terms restricting commercial use; check Google's policies, as the free model might be for personal or experimental purposes only.

gemini-cli-proxy

MITPython

Wrap the Gemini CLI as an OpenAI-compatible API service to use the free Gemini Pro model via standard API calls.

GitHub

What is gemini-cli-proxy?

Gemini CLI Proxy is a Python service that wraps Google's official Gemini CLI, exposing it as an OpenAI-compatible HTTP API server. It solves the problem of accessing the free Gemini 2.5 Pro model programmatically, enabling developers to use standard OpenAI client libraries and tools with Gemini.

Target Audience

Developers and hobbyists building AI-powered applications who want to use Google's Gemini model via a standard API interface without paying for commercial API services.

Value Proposition

It provides a free, self-hosted alternative to paid LLM APIs by leveraging Google's Gemini CLI, with full OpenAI API compatibility for easy integration into existing workflows and tools like Cherry Studio.

Overview

Wrap Gemini CLI as an OpenAI-compatible API service, allowing you to enjoy the free Gemini Pro model through API!

Use Cases

Best For

Adding a free LLM backend to personal or experimental AI projects
Testing AI features with a Gemini model using OpenAI client libraries

Related Projects

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub

147 stars26 forks0 contributors

Self-hosting an LLM API for development and prototyping

Integrating Gemini into applications that expect an OpenAI-compatible endpoint

Using AI tools like Cherry Studio with the Gemini model locally

Creating a cost-effective alternative to paid OpenAI API calls for non-commercial use

Not Ideal For

Production applications requiring high uptime and reliable network access to Google services
Teams operating in regions with strict internet censorship or no proxy access
Projects needing advanced OpenAI API features like streaming, function calling, or embeddings
Environments where installing and managing multiple dependencies (Node.js for Gemini CLI, Python for proxy) is prohibitive

Pros & Cons

Pros

Seamless OpenAI Integration

Implements the /v1/chat/completions endpoint exactly, allowing drop-in replacement with existing OpenAI client libraries, as demonstrated in the Python and Cherry Studio examples.

Quick Local Setup

Zero-configuration startup via uvx or standard Python tooling gets the service running in minutes, with clear commands provided in the README.

Cost-Effective Model Access

Leverages the free Gemini 2.5 Pro model through Google's CLI, offering a no-cost alternative to paid LLM APIs for development and prototyping.

Flexible Server Configuration

Allows customization of host, port, rate limits, and concurrency via command-line arguments, adapting to different local or network environments.

Cons

Network Dependency and Proxy Hassles

Requires manual proxy configuration in certain regions to access Google services, leading to frequent timeouts and connectivity issues, as admitted in the FAQ.

Reliance on External CLI Tool

Depends on Google's Gemini CLI, which adds complexity and potential breakage if the CLI changes or has bugs, since this proxy merely wraps it.

Limited Feature Parity

Only supports basic chat completions; lacks advanced OpenAI API features like streaming responses, function calling, or fine-tuning, limiting its use in sophisticated applications.

Minimal Authentication

Uses a dummy API key for all requests, providing no real security, which makes it unsuitable for multi-user or exposed deployments without additional layers.

Frequently Asked Questions

Home

Gemini CLI

gemini-cli-openai

Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers

Stars886

Forks211

Last commit1 month ago

geminicli2api

Gemini CLI to API Proxy is a FastAPI-based server that converts the Gemini CLI tool into standard API endpoints. It enables developers to use Google's free Gemini API quota through familiar OpenAI API interfaces or direct Gemini API calls, making it simple to integrate Gemini capabilities into existing applications. ## Key Features - **OpenAI-Compatible API** — Drop-in replacement for OpenAI's chat completions API, allowing seamless integration with tools expecting OpenAI's format. - **Native Gemini API** — Direct proxy to Google's Gemini API, supporting all its endpoints and features. - **Streaming Support** — Real-time streaming responses for both API formats, enabling interactive applications. - **Multimodal Support** — Handles text and image inputs, leveraging Gemini's multimodal capabilities. - **Authentication Flexibility** — Supports multiple auth methods including Bearer tokens, Basic auth, query parameters, and Google API headers. - **Model Variants** — Automatically creates model variants with Google Search grounding and thinking/reasoning controls. - **Docker Ready** — Containerized for easy deployment and includes Hugging Face Spaces compatibility. ## Philosophy The project aims to bridge the gap between Google's Gemini CLI and the broader ecosystem of AI tools by providing a standardized, easy-to-deploy API layer that maintains compatibility with popular interfaces.

Stars590

Forks632

Last commit5 months ago

Gemini CLI Termux

Gemini-CLI-Termux is an automated deployment tool designed specifically for the Android Termux environment. It enables users to easily run a reverse proxy service for Google's Gemini AI models on their mobile devices, providing OpenAI-compatible API endpoints. This makes advanced AI capabilities accessible directly from a smartphone, turning it into a local API server. ## Key Features - **One-Click Deployment** — Single command installs and configures the entire service with an interactive menu. - **OpenAI-Compatible API** — Provides `/v1/chat/completions` and `/v1/models` endpoints for seamless integration with existing tools. - **Full Gemini Model Support** — Supports Gemini 3.1 Pro, 3 Pro, 3 Flash, 2.5 Pro, and 2.5 Flash series, including search-enhanced and thinking variants. - **Multiple Authentication Methods** — Includes HTTP Basic Auth, Bearer Token, API Key query parameter, and Google API Key header support. - **LAN Accessibility** — Configurable to allow network listening, enabling other devices on the same network to use the API. - **Interactive Management Menu** — Visual interface for service control, configuration changes, and system maintenance without command-line expertise. ## Philosophy The project prioritizes mobile-first, zero-friction deployment, bringing powerful AI API hosting to Android devices through a simplified, menu-driven experience.

Stars169

Forks23

Last commit2 months ago

gemini-cli-mcp-openai-bridge

Gemini CLI Bridge is a server application built on top of Google's Gemini CLI. It exposes Gemini CLI's native tools via the Model Context Protocol (MCP) and provides a fully compatible OpenAI API endpoint, enabling seamless integration with third-party applications like Open WebUI. ## Key Features - **MCP Toolkit** — Exposes Gemini CLI's built-in tools (file operations, web search, content understanding) through a unified MCP endpoint. - **OpenAI API Bridge** — Provides `/v1/chat/completions` and `/v1/models` endpoints compatible with OpenAI's API, allowing any OpenAI-supporting tool to use Gemini models. - **External MCP Aggregation** — Acts as an MCP hub to connect and proxy tools from external MCP servers (in configured or YOLO modes). - **Flexible Security Policies** — Implements configurable security modes (read-only, edit, configured, yolo) to control tool execution and file operation scope. - **Inherited Authentication** — Uses the same authentication and configuration as the main Gemini CLI tool, requiring no duplicate setup. ## Philosophy The project prioritizes security and extensibility, providing a bridge that unlocks Gemini CLI's capabilities for the broader ecosystem while maintaining granular control over tool access and execution risks.

Stars138

Forks30

Last commit10 months ago