← Blog
2026-06-20

Bring your own model: connecting any OpenAI-compatible endpoint

Odysseus doesn't lock you to one model. If an endpoint speaks the OpenAI-compatible API (/v1/chat/completions), you can connect it.

How to connect a model

  1. In your workspace, open Settings → Model endpoints (or type /setup).
  2. Paste the base URL (ending in /v1) and an API key if the provider needs one.
  3. Pick the model and start chatting — instantly.

What works

OpenAI, OpenRouter, Together, DeepInfra, Fireworks, or your own vLLM / Ollama server. New workspaces also come with a managed model already connected, so you can chat the moment it boots.

See the full setup guide.

Start your private workspace →
· Ithaca Cloud