# 🧩 One Address → Free AI From Many Providers, Auto-Failover

**URL:** <https://onehack.st/t/one-address-free-ai-from-many-providers-auto-failover/323003>\
**Category:** Tutorials & Methods\
**Tags:** programming, tips-tricks, ai\
**Created:** [جون 13, 2026, 8:17am UTC](https://onehack.st/t/one-address-free-ai-from-many-providers-auto-failover/323003 "2026-06-13T08:17:15Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![BCBC](https://onehack.st/user_avatar/onehack.st/bcbc/32/180083_2.png) [@BCBC](https://onehack.st/u/BCBC)\
**Post date:** [جون 13, 2026, 8:17am UTC](https://onehack.st/t/one-address-free-ai-from-many-providers-auto-failover/323003/1 "2026-06-13T08:17:16Z")

</div>

### 🆓 Milk Multiple Free AI Tiers Through One Local API — Apps Hit a Single Endpoint While FreeLLMAPI Spreads Requests Across Free Providers and Auto-Recovers; Docker Compose Deploy With Logs and Checks

_Point any ChatGPT app at YOUR box. It juggles multiple free AI backends behind the scenes._

`homelab` · `ai` · `self-hosting`

> _Big thanks to SRZ from OneHack for the original FreeLLMAPI thread and bringing it to the community — this is my BCBC lab writeup of getting it running._

**The whole idea in one breath:** FreeLLMAPI is a little middleman _(a forwarder that sits between your app and the AI)_ that **pretends to be ChatGPT’s API** _(the address apps send AI requests to)_. So any tool built for ChatGPT talks to it without changes — but behind the curtain it routes to **a bunch of free AI providers** , and if one’s down or rate-limited, it **auto-jumps to the next.** One address, many free brains, zero app rewrites.

* * *

### 🎯 Why You’d Want This

🔌 **One endpoint, swap brains freely** — apps point at your box, you change providers behind it whenever.  
🪂 **Auto-fallback** — provider rate-limits you or dies? It silently switches to the next. No babysitting.  
🏠 **Runs local on your own server** — your traffic, your rules.  
🆓 **Stack free providers** — milk multiple free AI tiers through one door.

> 🧪 **Not hype — repeatable.** The point isn’t a flashy demo. It’s infrastructure you can stand up the same way twice and actually rely on.

* * *

### 🧱 The Lab Setup

```plaintext
Proxmox CT: 109 (a mini-computer on the server)
Service: FreeLLMAPI
Runtime: Docker / docker compose
Port: 3001 (the "door number" it listens on)
Endpoint: /v1/chat/completions
Database: SQLite (tiny built-in data file)

```

**How a request flows:**

```plaintext
your app
  ↓
fake-OpenAI address (looks like ChatGPT's API)
  ↓
FreeLLMAPI gateway (the middleman)
  ↓
provider routing / fallback
  ↓
multiple free AI backends

```

* * *

### ✅ Current Status — All Green

🟢 Docker container starts clean  
🟢 SQLite database initializes  
🟢 Model + fallback seed runs _(loads which providers to try and in what order)_  
🟢 API listening on port **3001**  
🟢 Proxy endpoint live at `/v1/chat/completions`

* * *

> **🔍 Confirm It Yourself (logs)**
>
> ```bash
> pct exec 109 -- bash -lc "docker logs --tail 100 freellmapi-freellmapi-1"
> 
> ```
> 
> You want to see:
> 
> ```plaintext
> Database initialized
> Server running on http://[::]:3001
> Proxy endpoint: http://[::]:3001/v1/chat/completions
> 
> ```
> 
> Container up, database seeded, API listening, proxy live. 🎉

> **🛠️ Next Upgrades (my to-do)**
>
> 🚪 **nginx reverse proxy** — a doorman in front so you hit a clean URL, not a raw port.  
> 📟 **Health/status page** — see at a glance if it’s alive.  
> 🪂 **Test the fallback** — kill one provider on purpose, confirm it jumps.  
> 🖥 **Hook in Ollama** — _(runs AI models locally on your own machine)_ so you’ve got an offline backend too.  
> 📋 **Document safe config examples** — copy-paste ready for the next person.

* * *

> 💡 **Real homelab truth:** the AI service booted _faster_ than the network plumbing did. The full stack dragged in Proxmox, Docker, pfSense, ClouDNS, BIND split DNS _(your own private phonebook for internal names)_, nginx, and browser-cache gremlins. Totally normal — **the app is only one piece; the system is the work.** 🐺

* * *

_One door, many free AI brains, auto-failover. Who’s spinning this up on their own box — and which providers are you stacking behind it?_