[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-467":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":47,"readmeContent":48,"aiSummary":49,"trendingCount":16,"starSnapshotCount":16,"syncStatus":50,"lastSyncTime":51,"discoverSource":52},467,"gpt4free","xtekky\u002Fgpt4free","xtekky","The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3","https:\u002F\u002Ft.me\u002Fg4f_channel",null,"Python",66319,13573,487,6,0,8,38,131,24,45,"GNU General Public License v3.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"chatbot","chatbots","chatgpt","chatgpt-4","chatgpt-api","chatgpt-free","chatgpt4","deepseek","deepseek-api","deepseek-r1","gpt","gpt-4","gpt-4o","gpt4","gpt4-api","language-model","openai","openai-api","openai-chatgpt","reverse-engineering","2026-06-12 02:00:14","# GPT4Free (g4f)\n\n[![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fg4f)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fg4f) [![Docker Hub](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocker-hlohaus789%2Fg4f-blue)](https:\u002F\u002Fhub.docker.com\u002Fr\u002Fhlohaus789\u002Fg4f) [![License: GPL v3](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-GPLv3-red.svg)](https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fgpl-3.0.txt) [![PyPI Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fpersonalized-badge\u002Fg4f?period=total&units=INTERNATIONAL_SYSTEM&left_color=GREY&right_color=GREEN&left_text=downloads)](https:\u002F\u002Fpepy.tech\u002Fprojects\u002Fg4f) ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxtekky\u002Fgpt4free)\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fimages\u002F477107515-7f60c240-00fa-4c37-bf7f-ae5cc20906a1.png\" alt=\"GPT4Free logo\" height=\"200\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cspan style=\"background: linear-gradient(45deg, #12c2e9, #c471ed, #f64f59); -webkit-background-clip: text; -webkit-text-fill-color: transparent;\">\n    \u003Cstrong>Created by \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fxtekky\">@xtekky\u003C\u002Fa>,\u003Cbr> maintained by \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fhlohaus\">@hlohaus\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003C\u002Fspan>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n\u003Cspan>Support the project on\u003C\u002Fspan>\n      \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhlohaus\" target=\"_blank\" rel=\"noopener noreferrer\">\n        GitHub Sponsors\n      \u003C\u002Fa>\n      ❤️\n\u003C\u002Fp>\n\u003Cp align=\"center\">\nLive demo & docs: https:\u002F\u002Fg4f.dev | Documentation: https:\u002F\u002Fg4f.dev\u002Fdocs\n\u003C\u002Fp>\n\n---\n\nGPT4Free (g4f) is a community-driven project that aggregates multiple accessible providers and interfaces to make working with modern LLMs and media-generation models easier and more flexible. GPT4Free aims to offer multi-provider support, local GUI, OpenAI-compatible REST APIs, and convenient Python and JavaScript clients — all under a community-first license.\n\nThis README is a consolidated, improved, and complete guide to installing, running, and contributing to GPT4Free.\n\nTable of contents\n- [What’s included](#whats-included)\n- [Quick links](#quick-links)\n- [Requirements & compatibility](#requirements--compatibility)\n- [Installation](#installation)\n  - [Docker (recommended)](#docker-recommended)\n  - [Slim Docker image](#slim-docker-image)\n  - [Windows (.exe)](#windows-exe)\n  - [Python (pip \u002F from source \u002F partial installs)](#python-pip--from-source--partial-installs)\n- [Running the app](#running-the-app)\n  - [GUI (web client)](#gui-web-client)\n  - [FastAPI \u002F Interference API](#fastapi--interference-api)\n  - [CLI](#cli)\n  - [Optional provider login (desktop in container)](#optional-provider-login-desktop-in-container)\n- [Using the Python client](#using-the-python-client)\n  - [Synchronous text example](#synchronous-text-example)\n  - [Image generation example](#image-generation-example)\n  - [Async client example](#async-client-example)\n- [Using GPT4Free.js (browser JS client)](#using-gpt4freejs-browser-js-client)\n- [Providers & models (overview)](#providers--models-overview)\n- [Local inference & media](#local-inference--media)\n- [Configuration & customization](#configuration--customization)\n- [Running on smartphone](#running-on-smartphone)\n- [Interference API (OpenAI‑compatible)](#interference-api-openai-compatible)\n- [Examples & common patterns](#examples--common-patterns)\n- [Contributing](#contributing)\n  - [How to create a new provider](#how-to-create-a-new-provider)\n  - [How AI can help you write code](#how-ai-can-help-you-write-code)\n- [Security, privacy & takedown policy](#security-privacy--takedown-policy)\n- [Credits, contributors & attribution](#credits-contributors--attribution)\n- [Powered-by highlights](#powered-by-highlights)\n- [Changelog & releases](#changelog--releases)\n- [Manifesto \u002F Project principles](#manifesto--project-principles)\n- [License](#license)\n- [Contact & sponsorship](#contact--sponsorship)\n- [Appendix: Quick commands & examples](#appendix-quick-commands--examples)\n\n---\n\n## What’s included\n- Python client library and async client.\n- Optional local web GUI.\n- FastAPI-based OpenAI-compatible API (Interference API).\n- Official browser JS client (g4f.dev distribution).\n- Docker images (full and slim).\n- Multi-provider adapters (LLMs, media providers, local inference backends).\n- Tooling for image\u002Faudio\u002Fvideo generation and media persistence.\n\n---\n\n## Quick links\n- Website & docs: https:\u002F\u002Fg4f.dev | https:\u002F\u002Fg4f.dev\u002Fdocs  \n- PyPI: https:\u002F\u002Fpypi.org\u002Fproject\u002Fg4f  \n- Docker image: https:\u002F\u002Fhub.docker.com\u002Fr\u002Fhlohaus789\u002Fg4f  \n- Releases: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Freleases  \n- Issues: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Fissues  \n- Community: Telegram (https:\u002F\u002Ftelegram.me\u002Fg4f_channel) · Discord News (https:\u002F\u002Fdiscord.gg\u002F5E39JUWUFa) · Discord Support (https:\u002F\u002Fdiscord.gg\u002FqXA4Wf4Fsm)\n\n---\n\n## Requirements & compatibility\n- Python 3.10+ recommended.\n- Google Chrome\u002FChromium for providers using browser automation.\n- Docker for containerized deployment.\n- Works on x86_64 and arm64 (slim image supports both).\n- Some provider adapters may require platform-specific tooling (Chrome\u002FChromium, etc.). Check provider docs for details.\n\n---\n\n## Installation\n\n### Docker (recommended)\n1. Install Docker: https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F\n2. Create persistent directories:\n   - Example (Linux\u002FmacOS):\n     ```bash\n     mkdir -p ${PWD}\u002Fhar_and_cookies ${PWD}\u002Fgenerated_media\n     sudo chown -R 1200:1201 ${PWD}\u002Fhar_and_cookies ${PWD}\u002Fgenerated_media\n     ```\n3. Pull image:\n   ```bash\n   docker pull hlohaus789\u002Fg4f\n   ```\n4. Run container:\n   ```bash\n   docker run -p 8080:8080 -p 7900:7900 \\\n     --shm-size=\"2g\" \\\n     -v ${PWD}\u002Fhar_and_cookies:\u002Fapp\u002Fhar_and_cookies \\\n     -v ${PWD}\u002Fgenerated_media:\u002Fapp\u002Fgenerated_media \\\n     hlohaus789\u002Fg4f:latest\n   ```\nNotes:\n- Port 8080 serves GUI\u002FAPI; 7900 can expose a VNC-like desktop for provider logins (optional).\n- Increase --shm-size for heavier browser automation tasks.\n\n### Slim Docker image (x64 & arm64)\n```bash\nmkdir -p ${PWD}\u002Fhar_and_cookies ${PWD}\u002Fgenerated_media\nchown -R 1000:1000 ${PWD}\u002Fhar_and_cookies ${PWD}\u002Fgenerated_media\n\ndocker run \\\n  -p 1337:8080 -p 8080:8080 \\\n  -v ${PWD}\u002Fhar_and_cookies:\u002Fapp\u002Fhar_and_cookies \\\n  -v ${PWD}\u002Fgenerated_media:\u002Fapp\u002Fgenerated_media \\\n  hlohaus789\u002Fg4f:latest-slim\n```\nNotes:\n- The slim image can update the g4f package on startup and installs additional dependencies as needed.\n- In this example, the Interference API is mapped to 1337.\n\n### Windows Guide (.exe)\n\n👉 Check out the Windows launcher for GPT4Free:  \n🔗 [https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.exe](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.exe) 🚀  \n\n1. Download the release artifact `g4f.exe.zip` from:\n   https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Freleases\u002Flatest\n2. Unzip and run `g4f.exe`.\n3. Open GUI at: http:\u002F\u002Flocalhost:8080\u002Fchat\u002F\n4. If Windows Firewall blocks access, allow the application.\n\n### Python Installation (pip \u002F from source \u002F partial installs)\n\nPrerequisites:\n- Python 3.10+ (https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n- Chrome\u002FChromium for some providers.\n\nInstall from PyPI (recommended):\n```bash\npip install -U g4f[all]\n```\n\nPartial installs\n- To install only specific functionality, use optional extras groups. See docs\u002Frequirements.md in the project docs.\n\nInstall from source:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free.git\ncd gpt4free\npip install -r requirements.txt\npip install -e .\n```\n\nNotes:\n- Some features require Chrome\u002FChromium or other tools; follow provider-specific docs.\n\n---\n\n## Running the app\n\n### GUI (web client)\n- Run via Python:\n```python\nfrom g4f.gui import run_gui\nrun_gui()\n```\n- Or via CLI:\n```bash\npython -m g4f.cli gui --port 8080 --debug\n```\n- Open: http:\u002F\u002Flocalhost:8080\u002Fchat\u002F\n\n### FastAPI \u002F Interference API\n- Start FastAPI server:\n```bash\npython -m g4f --port 8080 --debug\n```\n- If using slim docker mapping, Interference API may be available at `http:\u002F\u002Flocalhost:1337\u002Fv1`\n- Swagger UI: `http:\u002F\u002Flocalhost:1337\u002Fdocs`\n\n### CLI\n- Start GUI server:\n```bash\npython -m g4f.cli gui --port 8080 --debug\n```\n\n### MCP Server\nGPT4Free now includes a Model Context Protocol (MCP) server that allows AI assistants like Claude to access web search, scraping, and image generation capabilities.\n\n**Starting the MCP server (stdio mode):**\n```bash\n# Using g4f command\ng4f mcp\n\n# Or using Python module\npython -m g4f.mcp\n```\n\n**Starting the MCP server (HTTP mode):**\n```bash\n# Start HTTP server on port 8765\ng4f mcp --http --port 8765\n\n# Custom host and port\ng4f mcp --http --host 127.0.0.1 --port 3000\n```\n\nHTTP mode provides:\n- `POST http:\u002F\u002Flocalhost:8765\u002Fmcp` - JSON-RPC endpoint\n- `GET http:\u002F\u002Flocalhost:8765\u002Fhealth` - Health check\n\n**Configuring with Claude Desktop:**\n\nAdd to your `claude_desktop_config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"gpt4free\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"g4f.mcp\"]\n    }\n  }\n}\n```\n\n**Available MCP Tools:**\n- `web_search` - Search the web using DuckDuckGo\n- `web_scrape` - Extract text content from web pages  \n- `image_generation` - Generate images from text prompts\n\nFor detailed MCP documentation, see [g4f\u002Fmcp\u002FREADME.md](g4f\u002Fmcp\u002FREADME.md)\n\n### Optional provider login (desktop within container)\n- Accessible at:\n  ```\n  http:\u002F\u002Flocalhost:7900\u002F?autoconnect=1&resize=scale&password=secret\n  ```\n- Useful for logging into web-based providers to obtain cookies\u002FHAR files.\n\n---\n\n## Using the Python client\n\nInstall:\n```bash\npip install -U g4f[all]\n```\n\nSynchronous text example:\n```python\nfrom g4f.client import Client\n\nclient = Client()\nresponse = client.chat.completions.create(\n    model=\"gpt-4o-mini\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello, how are you?\"}],\n    web_search=False\n)\nprint(response.choices[0].message.content)\n```\nExpected:\n```\nHello! How can I assist you today?\n```\n\nImage generation example:\n```python\nfrom g4f.client import Client\n\nclient = Client()\nresponse = client.images.generate(\n    model=\"flux\",\n    prompt=\"a white siamese cat\",\n    response_format=\"url\"\n)\nprint(f\"Generated image URL: {response.data[0].url}\")\n```\n\nAsync client example:\n```python\nfrom g4f.client import AsyncClient\nimport asyncio\n\nasync def main():\n    client = AsyncClient()\n    response = await client.chat.completions.create(\n        model=\"gpt-4o-mini\",\n        messages=[{\"role\": \"user\", \"content\": \"Explain quantum computing briefly\"}],\n    )\n    print(response.choices[0].message.content)\n\nasyncio.run(main())\n```\n\nNotes:\n- See the full API reference for streaming, tool-calling patterns, and advanced options: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fclient\n\n---\n\n## Using GPT4Free.js (browser JS client)\nUse the official JS client in the browser—no backend required.\n\nExample:\n```html\n\u003Cscript type=\"module\">\n  import Client from 'https:\u002F\u002Fg4f.dev\u002Fdist\u002Fjs\u002Fclient.js';\n\n  const client = new Client();\n  const result = await client.chat.completions.create({\n      model: 'gpt-4.1',  \u002F\u002F Or \"gpt-4o\", \"deepseek-v3\", etc.\n      messages: [{ role: 'user', content: 'Explain quantum computing' }]\n  });\n  console.log(result.choices[0].message.content);\n\u003C\u002Fscript>\n```\n\nNotes:\n- The JS client is distributed via the g4f.dev CDN for easy usage. Review CORS considerations and usage limits.\n\n---\n\n## Providers & models (overview)\n- GPT4Free integrates many providers including (but not limited to) OpenAI-compatible endpoints, PerplexityLabs, Gemini, MetaAI, Pollinations (media), and local inference backends.\n- Model availability and behavior depend on provider capabilities. See the providers doc for current, supported provider\u002Fmodel lists: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fproviders-and-models\n\nProvider requirements may include:\n- API keys or tokens (for authenticated providers)\n- Browser cookies \u002F HAR files for providers scraped via browser automation\n- Chrome\u002FChromium or headless browser tooling\n- Local model binaries and runtime (for local inference)\n\n---\n\n## Local inference & media\n- GPT4Free supports local inference backends. See [docs\u002Flocal.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Flocal.md) for supported runtimes and hardware guidance.\n- Media generation (image, audio, video) is supported through providers (e.g., Pollinations). See [docs\u002Fmedia.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fmedia.md) for formats, options, and sample usage.\n\n---\n\n## Configuration & customization\n- Configure via environment variables, CLI flags, or config files. See [docs\u002Fconfig.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fconfig.md).\n- To reduce install size, use partial requirement groups. See [docs\u002Frequirements.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Frequirements.md).\n- Provider selection: learn how to set defaults and override per-request at [docs\u002Fselecting_a_provider.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fselecting_a_provider.md).\n- Persistence: HAR files, cookies, and generated media persist in mapped directories (e.g., har_and_cookies, generated_media).\n\n---\n\n## Running on smartphone\n- The web GUI is responsive and can be accessed from a phone by visiting your host IP:8080 or via a tunnel. See [docs\u002Fguides\u002Fphone.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fphone.md).\n\n---\n\n## Interference API (OpenAI‑compatible)\n- The Interference API enables OpenAI-like workflows routed through GPT4Free provider selection.\n- Docs: [docs\u002Finterference-api.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Finterference-api.md)\n- Default endpoint (example slim docker): `http:\u002F\u002Flocalhost:1337\u002Fv1`\n- Swagger UI: `http:\u002F\u002Flocalhost:1337\u002Fdocs`\n\n---\n\n## Examples & common patterns\n- Streaming completions, stopping criteria, system messages, and tool-calling patterns are documented in:\n  - [docs\u002Fclient.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fclient.md)\n  - [docs\u002Fasync_client.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fasync_client.md)\n  - [docs\u002Frequests.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Frequests.md)\n- Integrations (LangChain, PydanticAI): [docs\u002Fpydantic_ai.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fpydantic_ai.md)\n- Legacy examples: [docs\u002Flegacy.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Flegacy.md)\n\n---\n\n## Contributing\nContributions are welcome — new providers, features, docs, and fixes are appreciated.\n\nHow to contribute:\n1. Fork the repository.\n2. Create a branch for your change.\n3. Run tests and linters.\n4. Open a Pull Request with a clear description and tests\u002Fexamples if applicable.\n\nRepository: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\n\n### How to create a new provider\n- Read the guide: [docs\u002Fguides\u002Fcreate_provider.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fcreate_provider.md)\n- Typical steps:\n  - Implement a provider adapter in `g4f\u002FProvider\u002F`\n  - Add configuration and dependency notes\n  - Include tests and usage examples\n  - Respect third‑party code licenses and attribute appropriately\n\n### How AI can help you write code\n- See: [docs\u002Fguides\u002Fhelp_me.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fhelp_me.md) for prompt templates and workflows to accelerate development.\n\n---\n\n## Security, privacy & takedown policy\n- Do not store or share sensitive credentials. Use per-provider recommended security practices.\n- If your site appears in the project’s links and you want it removed, send proof of ownership to takedown@g4f.ai and it will be removed promptly.\n- For production, secure the server with HTTPS, authentication, and firewall rules. Limit access to provider credentials and cookie\u002FHAR storage.\n\n---\n\n## Credits, contributors & attribution\n- Core creators: [@xtekky](https:\u002F\u002Fgithub.com\u002Fxtekky) (original), maintained by [@hlohaus](https:\u002F\u002Fgithub.com\u002Fhlohaus).\n- Full contributor graph: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Fgraphs\u002Fcontributors\n- Notable code inputs and attributions:\n  - `har_file.py` — input from [xqdoo00o\u002FChatGPT-to-API](https:\u002F\u002Fgithub.com\u002Fxqdoo00o\u002FChatGPT-to-API)\n  - `PerplexityLabs.py` — input from [nathanrchn\u002Fperplexityai](https:\u002F\u002Fgithub.com\u002Fnathanrchn\u002Fperplexityai)\n  - `Gemini.py` — input from [dsdanielpark\u002FGemini-API](https:\u002F\u002Fgithub.com\u002Fdsdanielpark\u002FGemini-API) and [HanaokaYuzu\u002FGemini-API](https:\u002F\u002Fgithub.com\u002FHanaokaYuzu\u002FGemini-API)\n  - `MetaAI.py` — inspired by [meta-ai-api by Strvm](https:\u002F\u002Fgithub.com\u002FStrvm\u002Fmeta-ai-api)\n  - `proofofwork.py` — input from [missuo\u002FFreeGPT35](https:\u002F\u002Fgithub.com\u002Fmissuo\u002FFreeGPT35)\n\nMany more contributors are acknowledged in the repository.\n\n---\n\n## Powered-by highlights\n- Pollinations AI — generative media: https:\u002F\u002Fgithub.com\u002Fpollinations\u002Fpollinations\n- MoneyPrinter V2 — example project using GPT4Free: https:\u002F\u002Fgithub.com\u002FFujiwaraChoki\u002FMoneyPrinterV2\n- For a full list of projects and sites using GPT4Free, see: [docs\u002Fpowered-by.md](https:\u002F\u002Fgithub.com\u002Fgpt4free\u002Fg4f.dev\u002Fblob\u002Fmain\u002Fdocs\u002Fpowered-by.md)\n\n---\n\n## Changelog & releases\n- Releases and full changelog: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Freleases\n- Subscribe to Discord\u002FTelegram for announcements.\n\n---\n\n## Manifesto \u002F Project principles\nGPT4Free is guided by community principles:\n1. Open access to AI tooling and models.\n2. Collaboration across providers and projects.\n3. Opposition to monopolistic, closed systems that restrict creativity.\n4. Community-centered development and broad access to AI technologies.\n5. Promote innovation, creativity, and accessibility.\n\nhttps:\u002F\u002Fg4f.dev\u002Fmanifesto\n\n---\n\n## License\nThis program is licensed under the GNU General Public License v3.0 (GPLv3). See the full license: https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fgpl-3.0.txt\n\nSummary:\n- You may redistribute and\u002For modify under the terms of GPLv3.\n- The program is provided WITHOUT ANY WARRANTY.\n\nCopyright notice\n```\nxtekky\u002Fgpt4free: Copyright (C) 2025 xtekky\n\nThis program is free software: you can redistribute it and\u002For modify\nit under the terms of the GNU General Public License as published by\nthe Free Software Foundation, either version 3 of the License, or\n(at your option) any later version.\n\nThis program is distributed in the hope that it will be useful,\nbut WITHOUT ANY WARRANTY; without even the implied warranty of\nMERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the\nGNU General Public License for more details.\n```\n\n---\n\n## Contact & sponsorship\n- Maintainers: https:\u002F\u002Fgithub.com\u002Fhlohaus  \n- Sponsorship: https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhlohaus  \n- Issues & feature requests: https:\u002F\u002Fgithub.com\u002Fxtekky\u002Fgpt4free\u002Fissues  \n- Takedown requests: takedown@g4f.ai\n\n---\n\n## Appendix: Quick commands & examples\n\nInstall (pip):\n```bash\npip install -U g4f[all]\n```\n\nRun GUI (Python):\n```bash\npython -m g4f.cli gui --port 8080 --debug\n# or\npython -c \"from g4f.gui import run_gui; run_gui()\"\n```\n\nDocker (full):\n```bash\ndocker pull hlohaus789\u002Fg4f\ndocker run -p 8080:8080 -p 7900:7900 \\\n  --shm-size=\"2g\" \\\n  -v ${PWD}\u002Fhar_and_cookies:\u002Fapp\u002Fhar_and_cookies \\\n  -v ${PWD}\u002Fgenerated_media:\u002Fapp\u002Fgenerated_media \\\n  hlohaus789\u002Fg4f:latest\n```\n\nDocker (slim):\n```bash\ndocker run -p 1337:8080 -p 8080:8080 \\\n  -v ${PWD}\u002Fhar_and_cookies:\u002Fapp\u002Fhar_and_cookies \\\n  -v ${PWD}\u002Fgenerated_media:\u002Fapp\u002Fgenerated_media \\\n  hlohaus789\u002Fg4f:latest-slim\n```\n\nPython usage patterns:\n- `client.chat.completions.create(...)`\n- `client.images.generate(...)`\n- Async variants via `AsyncClient`\n\nDocs & deeper reading\n- Full docs: https:\u002F\u002Fg4f.dev\u002Fdocs  \n- Client API docs: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fclient  \n- Async client docs: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fasync_client  \n- Provider guides: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Fproviders  \n- Local inference: https:\u002F\u002Fg4f.dev\u002Fdocs\u002Flocal\n\n---\n\nThank you for using and contributing to GPT4Free — together we make powerful AI tooling accessible, flexible, and community-driven.\n","GPT4Free 是一个社区驱动的项目，旨在通过聚合多个可访问的服务提供商和接口来简化与现代语言模型及媒体生成模型的工作。其核心功能包括多服务提供商支持、本地图形用户界面、兼容OpenAI的REST API以及便捷的Python和JavaScript客户端。该项目采用GPLv3许可证，强调社区优先。GPT4Free适用于需要灵活使用不同语言模型的应用场景，如构建聊天机器人、内容生成工具等。它为开发者提供了一个强大的平台，可以轻松集成最新的AI技术而无需直接支付高昂的API费用。",2,"2026-06-11 02:36:13","top_all"]