UnoRouter

UnoRouter is a unified AI gateway that connects to hundreds of models through one key. Point an OpenAI-compatible client at it and use a single endpoint across providers, with automatic provider failover built in.

It supports multiple workflows: coding agents, character & fiction clients, general chat clients, and CLI tools. That means you can keep your existing OpenAI-style integrations while choosing from a large set of available model names.

UnoRouter also includes a built-in chat experience. Free models can be used directly in the browser without setup, while private/BYOK chat keeps conversation data in your browser and lets you bring your own OpenAI-compatible endpoint and key.

What is UnoRouter?

UnoRouter is an open-source LLM gateway that exposes a fully OpenAI-compatible API so you can access many models through one endpoint and one key.

How do I connect my existing OpenAI-compatible client?

Use your UnoRouter API key with the OpenAI-compatible chat/completions endpoint. Your client sends requests like normal, and UnoRouter routes them to the selected model.

Does UnoRouter support automatic provider failover?

Yes—provider failover is designed to keep requests going when upstream providers aren’t available.

Can I use UnoRouter with character chat clients like SillyTavern?

Yes. UnoRouter is compatible with character & fiction clients such as SillyTavern, Janitor.AI, Chub, and RisuAI.

Is there a chat mode that doesn’t require setup or an API key?

Yes—there’s a built-in chat where free models are wired in on the backend, so you can open and chat without signup or key.

What does “private & BYOK” mean for character chat?

Conversations live in your browser, and you can bring your own OpenAI-compatible endpoint and key for browser-fired requests.