Search any model
Show vision models
Route to the fastest
Switch to auto
Qwen
Gemini
DeepSeek
Kimi

CENOTE ROUTER

One free key. Every AI model. Say what you need, Cenote routes it.

Now routing
Purchases and premium access are handled on our Discord server. The router itself is free to self-host.
Join on Discord →
free tokens routed 0 next +200 in --:--
cenote://router

AI models

Search, filter by tag, and open any model for its description and ready-to-copy code.

Smart router

Describe a task and watch Cenote pick the best free model. Interactive demo with simple built-in rules.

Use it

Cenote Router is a self-hosted router you run yourself. Install it, paste in your free key, and glm-5.3:free answers on an OpenAI-compatible endpoint at http://localhost:3001/v1. No credit card, no hosted middleman: your prompts and your provider keys never leave your machine.

Install the router (macOS, Linux, WSL)

curl -fsSL https://freellmapi.co/install.sh | bash

Install the router (Windows PowerShell)

iwr -useb https://freellmapi.co/install.ps1 | iex

The router answers on /v1/chat/completions and every other OpenAI surface, plus the Anthropic Messages API, so existing clients need only a new base_url. Use the model id auto and the router picks the best free model that is still under its limits.

Go live for $5 a year

Click a plan to join our Discord and buy there. Cancel anytime.

ANNUAL
$5 / year
  • The live catalog, on every device
  • New free models and fixes as they ship
  • Cancel anytime
Go live on Discord →
LIFETIME
$15 once
  • Everything in Annual, forever
  • No renewals, ever
  • One key, all surfaces
Buy Lifetime on Discord →

FAQ


Is it really free?

The router is free to self-host. Each provider meters its own free tier, and availability varies.

How do I buy Premium?

Join our Discord server using any “Go live” button and follow the steps there.

Do my prompts leave my machine?

No hosted middleman: requests go from your router straight to the providers you configure.

Which clients work?

Anything that speaks the OpenAI API or the Anthropic Messages API — just change the base_url.