FreeToken · free AI tokens for everyone

Pool every free AI tier — Gemini, Groq, OpenRouter, NVIDIA, Cohere, GitHub Models and more — into
one chat, one OpenAI-compatible API, and V-Run, a desktop AI coding agent. $0, no credit card, self-hosted.

Quick start · Features · V-Run desktop app · FAQ

_{A V Groups project · if it saves you money, a ⭐ helps others find it}

💡 What is FreeToken?

Every AI company gives away a free tier — Google Gemini, Groq, OpenRouter, NVIDIA NIM, Cohere, GitHub Models… On its own each one runs out fast. FreeToken pools them. Add the free API keys you sign up for (no card needed for most), and every request goes to whichever provider still has quota, falling back automatically the moment one is rate-limited.

You get free AI tokens through:

• 💬 A chat app — like ChatGPT, but running on every free model you have.
• 🔌 Your own OpenAI-compatible API — point Cursor, Continue, Cline, LangChain or your scripts at it: base_url=http://localhost:3000/api/v1.
• 🖥️ V-Run — a desktop AI code editor (think Cursor / Claude Code) whose agent writes code, runs your app and fixes what it sees — on free models.

Your keys are encrypted and used only for your requests. Nothing is shared, nothing is billed.

  Gemini ┐
  Groq   ┤                      ┌─► 💬 Chat
  NVIDIA ┼──►  FreeToken router ┼─► 🔌 OpenAI-compatible API
  Cohere ┤     (auto-failover)  └─► 🖥️ V-Run coding agent
  GitHub ┘

⚡ Quick start (one line)

Windows (PowerShell):

irm https://raw.githubusercontent.com/V-Groups-Foundations/freetoken/master/install.ps1 | iex

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/V-Groups-Foundations/freetoken/master/install.sh | bash

That's it. Your browser opens already signed in (no account, no password — a private link only your computer has), and chat works immediately with the built-in starter model — no API key needed.

Then make it fast: on Connect, click Get key for Gemini or Groq, copy the key on their page, and come back — it's added automatically. OpenRouter is one click. Already have keys? Paste them all at once (or a whole .env file) and FreeToken recognises each one.

You need Node.js 20.9+. The database is built in.

git clone https://github.com/V-Groups-Foundations/freetoken.git
cd freetoken
npm install
npm run dev       # sets itself up, then opens http://localhost:3000 signed in

Want the desktop coding agent too?

npm run desktop   # builds and opens V-Run — it starts FreeToken and connects itself

🤖 Claude Code, Cursor & Cline — on free models

FreeToken speaks both the OpenAI API (/api/v1/chat/completions) and the Anthropic API (/api/v1/messages, with streaming and tool use), so the AI tools you already use run on your free pool:

freetoken run claude              # Claude Code, on free models (in this folder: npm run claude)
freetoken run aider --model openai/auto-smart
freetoken setup cursor            # copy-paste setup for Cursor, Cline, Continue, Codex, OpenCode…

freetoken run only sets the environment for that one run — your tool's own settings are untouched. Claude model names map to FreeToken automatically (haiku → auto-fast, everything else → auto-smart). The API page in the app shows the same setup with your URLs.

📸 Screenshots

V-Run: the agent edits, runs and verifies	V-Run: your FreeToken hub
FreeToken on the web	The V Groups family

🚀 What you get

🖥️ V-Run — the free AI coding agent

desktop/ is V-Run, a desktop AI code editor (Electron + Monaco) — a free alternative to Cursor and Claude Code that runs on your FreeToken models (or Claude, with your own key).

• Agent, Plan and Ask modes — the agent reads, searches, edits files and runs commands; Plan mode proposes a plan you approve first.
• Accept all or step by step — chosen once per task, so it never nags you mid-job.
• Runs your app — starts your web app inside the editor, sees the page and its console errors, and fixes them. One-click Fix with AI on crashes.
• Diffs, rewind and retry — every edit shown as a diff; rewind any message to undo its file changes.
• Memory with V.md — like CLAUDE.md: /init writes your project's memory, # note adds to it, and the agent remembers lasting facts on its own.
• Visible reasoning, follow-up suggestions, @file mentions, Tab completion and Ctrl+K inline edits.
• FreeToken built in — sign in with one click, browse projects, usage and models in the FreeToken hub, and Continue in V-Run from any FreeToken project (its turns are saved back to the web chat).

🔑 Free providers you can connect

Optional tools: Tavily (web search) · DeepL (translation) · Jina (embeddings) · OCR.space (scanned files) · ElevenLabs / Google TTS (voices).

❓ FAQ

Yes. FreeToken is open source (MIT) and runs on your machine. It uses the free tiers that AI providers already offer; you sign up for them yourself (most need no credit card). FreeToken just makes them work together — no subscription, no hidden costs. Out of the box it also includes a keyless starter model (via Pollinations's free tier) so you can try everything before adding a single key; it's shared and rate-limited, so add your own free keys for real use, and set FREETOKEN_STARTER=off to turn it off.

From your own free accounts with each provider. FreeToken doesn't resell or share anyone's quota — it routes your requests across your free tiers so you rarely hit a limit.

Yes — create a token under API and use http://localhost:3000/api/v1 as an OpenAI base URL with model auto-smart.

They're encrypted at rest with your own VAULT_MASTER_KEY (generated on first start) and only ever sent to the provider they belong to. Signing in on your own computer uses a random link that changes every start and is readable only on your machine (like Jupyter's token); set FREETOKEN_LOCAL_LOGIN=off if you host FreeToken for others.

Same idea — an editor with an agent that edits code and runs commands — but it's free, open source, runs on free models through FreeToken, and can run and look at your app while it works.

🧱 Tech stack

Next.js 16 · React 19 · TypeScript · Drizzle ORM · PGlite (embedded Postgres) · Auth.js v5 · Tailwind v4 · Vitest — and for V-Run: Electron · Monaco · Vite.

🤝 Contributing

Contributions are very welcome — see CONTRIBUTING.md. Good first steps: add a free provider, improve the docs, or try V-Run and open an issue with what you'd like next.

⭐ Support the project

FreeToken is free and will stay free. If it helps you, star the repo and share it — that's how other people find free AI tools.

📄 License

MIT — see LICENSE. Use it, fork it, share it.