# 🤖 Free AI instead of ChatGPT and Claude — 34 providers, 635 endpoints, one key

**URL:** <https://onehack.st/t/free-ai-instead-of-chatgpt-and-claude-34-providers-635-endpoints-one-key/326626>\
**Category:** Tools & Scripts\
**Tags:** programming, freebies, ai\
**Created:** [October 20, 2026, 10:36pm UTC](https://onehack.st/t/free-ai-instead-of-chatgpt-and-claude-34-providers-635-endpoints-one-key/326626 "2026-10-20T22:36:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![SRZ](https://onehack.st/user_avatar/onehack.st/srz/32/146132_2.png) [@SRZ](https://onehack.st/u/SRZ)\
**Post date:** [October 20, 2026, 10:36pm UTC](https://onehack.st/t/free-ai-instead-of-chatgpt-and-claude-34-providers-635-endpoints-one-key/326626/1 "2026-10-20T22:36:27Z")

</div>

![free AI, one key, replaces the big ones](https://onehack.st/uploads/default/original/3X/0/3/031bb17834cb6ca527c862696e2d2d8ef194ca61.jpeg)

# 🔑 One key for every free AI model

**Free AI is not scarce any more — keys are.** Every provider hands out a little, and pooled behind one endpoint those little bits become something you can build on all day. ⚡

**What that one key gives you**

- 💬 chat with the frontier models
- ⌨ coding inside opencode, Cline, Aider or Continue
- 🤖 agents that run your scripts and tools

**The pools — pick one and you are set**

- **[FreeLLMAPI](https://github.com/tashfeenahmed/freellmapi)** ★38k · MIT — 34 providers, 635 free endpoints, 7.4B tokens a month behind a single `/v1`
- **[freellmpool](https://github.com/0xzr/freellmpool)** ★128 — 23 providers, 178 routes, starts without a key
- **[LiteLLM](https://github.com/BerriAI/litellm)** ★62k — self-hosted proxy covering 140+ providers
- **[free-router](https://github.com/www222fff/free-router)** ★478 · **[CliRelay](https://github.com/kittors/CliRelay)** ★1k — model ranking, and CLI logins bridged into one endpoint

**When a key runs out — and it will**

- 🔁 **[new-api](https://github.com/Calcium-Ion/new-api)** ★50k — hold every key you own, rotate and retry automatically
- 🧭 **[LiteLLM router](https://github.com/BerriAI/litellm)** — fallbacks, retries and cooldowns in one config
- ☁ **[Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/)** · 🔀 **[OpenRouter routing](https://openrouter.ai/docs/features/model-routing)** — hosted fallbacks, no server to keep alive

**Keys with no card and no phone** — [Google AI Studio](https://aistudio.google.com) · [Groq](https://console.groq.com) · [Cerebras](https://www.cerebras.ai) · [SambaNova](https://sambanova.ai) · [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) · [NVIDIA NIM](https://build.nvidia.com/models) · [Hugging Face](https://huggingface.co/docs/inference-providers) · [GLM on z.ai](https://z.ai) · [OpenRouter](https://openrouter.ai) · and [DuckDuckGo AI](https://duck.ai) asks for nothing at all

**Agents, all free** — [opencode](https://github.com/sst/opencode) ★219k · [Gemini CLI](https://github.com/google-gemini/gemini-cli) ★107k · [Cline](https://github.com/cline/cline) ★71k · [Aider](https://github.com/Aider-AI/aider) ★50k · [Continue](https://github.com/continuedev/continue) ★36k — or keep it offline with [Ollama](https://github.com/ollama/ollama) ★184k and [Open WebUI](https://github.com/open-webui/open-webui) ★156k

**Three moves to start** — install **opencode** → paste the FreeLLMAPI key → put **new-api** in front so a dead key never reaches you ⚡

**Honest note** — free tiers are rate-limited, and the rotation layer is how people work around it. Worth reading each provider’s data policy before pasting company code 🧠

**Directories that stay updated** — [itsfree.ai](https://itsfree.ai) · [freeinference.dev](https://freeinference.dev) · [freellmapi.co](https://freellmapi.co)