Gemini Web API

OpenAI-compatible Gemini Web API reverse proxy running on Bun & Node.js. Automatically detects Chrome session cookies. Zero configuration required.

兼容 OpenAI 格式的 Gemini Web 反向代理服务，支持 Bun 与 Node.js 双运行时。 全自动探测本地 Chrome 凭据，无需任何手动配置，开箱即用。

English

Overview

@8-/gemini-web-api is an ultra-lightweight reverse proxy that turns your Google Gemini Web session into a standard OpenAI-compatible API.

No configuration is needed: It automatically discovers your existing Chrome / Brave / Edge browser session, retrieves the encryption key from the macOS Keychain, decrypts your Gemini session cookies, and starts serving OpenAI-compatible endpoints (/v1/chat/completions, /v1/models) instantly.

Key Highlights

• Zero Configuration: As long as you are logged into gemini.google.com in Chrome (or Brave / Edge), the server automatically extracts and decrypts your tokens. No manual cookie copying or .env required!
• Dual Runtime Support: Native ultra-high performance on Bun (Bun.serve) and seamless native support on Node.js (>= 22.5.0, via node:sqlite and Web Streams).
• Zero External Dependencies: 100% built on standard Web APIs (fetch, ReadableStream, crypto.subtle) and built-in Node/Bun modules. Zero node_modules required!
• OpenAI Drop-in Replacement: Fully compatible with /v1/chat/completions and /v1/models. Works seamlessly with ChatGPT-Next-Web, LobeChat, Cherry Studio, Cline, Roo Code, Cursor, Aider, and official OpenAI SDKs.
• Robust 4-Tier Tool / Function Calling Engine:
  1. Tier 1 (Fenced Code Blocks): Parses ```tool_call, ```tool_calls, ```json, or bare ``` blocks.
  2. Tier 2 (Tool Call Arrays): Extracts structured "tool_calls": [...] arrays embedded in output.
  3. Tier 3 (Unfenced / Broken Fences): Recovers missing opening backticks (e.g. `tool_call\n{...}````).
  4. Tier 4 (Bare JSON Objects): Bracket-matched scanner for raw JSON objects with name and arguments/args/input.
  • Auto Syntax Healing: Automatically cleans escaped markdown underscores (subagent\_type → subagent_type), trailing commas, unquoted keys, and invalid escapes.
  • Framework Agnostic: Natively normalizes tool call formats from Vercel AI SDK, ZCode, LangChain, and OpenAI SDKs (toolCalls, input, toolName, toolCallId).
• Reasoning & Thinking Models: Full support for <think> thoughts and reasoning_content deltas in SSE streaming with an automatic tag closure state machine, as well as reasoning_content in non-streaming responses.
• Dynamic Model Discovery: Automatically discovers available Gemini models (Flash, Pro, etc.) and capacity tiers directly from your web session.
• Image Proxy: Built-in /gemini-proxy/image endpoint to safely render generated card images without CORS or anti-hotlinking issues.

Installation

Install globally using Bun or npm:

# Using Bun
bun i -g @8-/gemini-web-api

# Using npm
npm i -g @8-/gemini-web-api

Or run instantly without installing:

# Using bunx
bunx @8-/gemini-web-api

# Using npx
npx @8-/gemini-web-api

Usage

1. Start the Server

Simply run:

gemini-web-api

The server will automatically:

1. Detect your local Chrome / Brave / Edge cookies database.
2. Read the encryption key from macOS Keychain.
3. Decrypt your __Secure-1PSID and __Secure-1PSIDTS cookies.
4. Discover available models from Gemini.
5. Start listening on http://127.0.0.1:7860.

2. Optional Environment Variables

If you want to customize the port, add an authentication key, or enable thinking mode, set environment variables inline or in a .env file:

# Example: Custom port, API key, and thinking mode
PORT=8000 API_KEY=sk-mysecret ENABLE_THINKING=true gemini-web-api

| Variable | Default | Description | | :--- | :--- | :--- | | PORT | 7860 | Server listening port | | HOST | 127.0.0.1 | Server listening host | | API_KEY | (empty) | Optional Bearer API key for authorization | | ENABLE_THINKING | false | Enable reasoning thoughts (<think> blocks & reasoning_content) | | SECURE_1PSID | (auto-detected) | Manual override for __Secure-1PSID cookie (only needed if no browser is logged in) | | SECURE_1PSIDTS | (auto-detected) | Manual override for __Secure-1PSIDTS cookie |

API Calling Examples

1. Streaming Chat (cURL)

curl -N http://127.0.0.1:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-flash",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one sentence."}
    ],
    "stream": true
  }'

2. Function Calling / Tool Calling (Python SDK)

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:7860/v1",
    api_key="none"
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a city.",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="gemini-flash",
    messages=[{"role": "user", "content": "What is the weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto"
)

message = response.choices[0].message
if message.tool_calls:
    for tool_call in message.tool_calls:
        print(f"Tool: {tool_call.function.name}")
        print(f"Arguments: {tool_call.function.arguments}")

3. Streaming Chat with Node.js SDK

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://127.0.0.1:7860/v1",
  apiKey: "none",
});

const stream = await openai.chat.completions.create({
  model: "gemini-flash",
  messages: [{ role: "user", content: "Tell me a short joke." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

简体中文

项目简介

@8-/gemini-web-api 是一个极简的 Google Gemini Web 转 OpenAI 标准接口反向代理服务。

无需繁琐配置：只需在日常使用的 Chrome（或 Brave、Edge）浏览器中登录过 gemini.google.com，程序启动时即可全自动探测浏览器 Cookie 数据库，通过 macOS Keychain 提取密钥并自动解密登录凭据，立即开始提供兼容 OpenAI 的 /v1/chat/completions 与 /v1/models 接口！

核心亮点

• 开箱即用，零手动配置：自动探测 Chrome / Brave / Edge 浏览器会话，全自动解密并获取登录令牌，彻底告别手动抓包复制 Cookie 的烦恼！
• Bun 与 Node.js 双运行时支持：在 Bun 下使用原生 Bun.serve 极速响应；在 Node.js (>= 22.5.0) 下利用内置 node:sqlite 与原生 Web Streams 同样流畅运行。
• 零第三方外部依赖：纯基于 Web 标准接口（fetch、ReadableStream、crypto.subtle）与运行时内置标准模块构建，零 node_modules 外部依赖！
• 无缝替代 OpenAI 接口：标准 /v1/chat/completions 与 /v1/models 路由，直接兼容 ChatGPT-Next-Web、LobeChat、Cherry Studio、Cline、Roo Code、Cursor、Aider 以及官方 OpenAI SDK。
• 四级高鲁棒性 Function Calling / 工具调用引擎：
  1. 第一级（围栏代码块）：精确解析 ```tool_call、```tool_calls、```json 或裸反引号代码块。
  2. 第二级（数组提取）：自动提取内嵌于回复中的 "tool_calls": [...] 结构体。
  3. 第三级（缺失开头围栏容错）：支持缺失开头反引号等残缺输出自愈（如 `tool_call\n{...}````）。
  4. 第四级（无围栏裸 JSON 深度探测）：括号平衡算法精确提取包含 name 与 arguments/args/input 的独立 JSON 对象，游标防跳步确保多个紧邻调用不遗漏。
  • 语法自动修复：自动反转义 Markdown 下划线（subagent\_type → subagent_type），智能修复未加引号的键名与尾随逗号。
  • 框架协议泛化：原生兼容 Vercel AI SDK、ZCode、LangChain 及各类 Agent 框架自定义字段（toolCalls、input、toolName、toolCallId）。
• 深度思考与推理模式：完整支持 <think> 思考标签与 SSE reasoning_content 流式字段传输，内置状态机保证思考标签严格闭合，且在非流式调用中完整保留思考链。
• 动态模型列表发现：启动时自动从 Gemini 网页端动态拉取已解锁的可用模型及配额层级。
• 图片安全代理：内置 /gemini-proxy/image 接口，解决 Google 生成图片防盗链和跨域展示问题。

安装方式

通过 Bun 或 npm 全局安装：

# 使用 Bun 全局安装
bun i -g @8-/gemini-web-api

# 使用 npm 全局安装
npm i -g @8-/gemini-web-api

或者无需安装，直接使用 bunx / npx 即开即用：

# 使用 bunx
bunx @8-/gemini-web-api

# 使用 npx
npx @8-/gemini-web-api

使用指南

1. 启动服务

安装后直接在终端运行：

gemini-web-api

程序将全自动执行：

1. 自动探测本地 Chrome、Brave、Edge 浏览器的 Cookie 存储路径；
2. 自动从 macOS Keychain 安全读取加密密码并推导密钥；
3. 解密 __Secure-1PSID 与 __Secure-1PSIDTS 凭据；
4. 动态同步 Gemini 网页端模型配置；
5. 在 http://127.0.0.1:7860 启动 OpenAI 兼容接口。

2. 可选环境变量配置

如需自定义端口、设置访问密码或启用思考模式，可在命令行直接传入或在当前目录下创建 .env 文件：

# 示例：自定义端口 8000、密码及开启思考模式
PORT=8000 API_KEY=sk-mysecret ENABLE_THINKING=true gemini-web-api

| 环境变量 | 默认值 | 说明 | | :--- | :--- | :--- | | PORT | 7860 | 服务的监听端口 | | HOST | 127.0.0.1 | 监听的主机地址 | | API_KEY | (留空) | 可选的 Bearer 访问密码鉴权 | | ENABLE_THINKING | false | 是否开启思考模式（输出 <think> 与 reasoning_content） | | SECURE_1PSID | (自动探测) | 手动指定 __Secure-1PSID（仅在未登录浏览器时需要） | | SECURE_1PSIDTS | (自动探测) | 手动指定 __Secure-1PSIDTS |

接口调用示例

1. cURL 流式对话调用

curl -N http://127.0.0.1:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-flash",
    "messages": [
      {"role": "user", "content": "用一句话解释相对论"}
    ],
    "stream": true
  }'

2. 工具调用 / Function Calling (Python SDK)

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:7860/v1",
    api_key="none"  # 未设置 API_KEY 时可填任意字符串
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "查询指定城市的天气温度",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="gemini-flash",
    messages=[{"role": "user", "content": "查询东京的天气"}],
    tools=tools,
    tool_choice="auto"
)

message = response.choices[0].message
if message.tool_calls:
    for tool_call in message.tool_calls:
        print(f"触发工具: {tool_call.function.name}, 参数: {tool_call.function.arguments}")

3. Node.js 流式对话 (OpenAI SDK)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://127.0.0.1:7860/v1",
  apiKey: "none",
});

const stream = await openai.chat.completions.create({
  model: "gemini-flash",
  messages: [{ role: "user", content: "讲个笑话吧" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

开源协议

本项目采用 MIT License 授权。