Notes on running models yourself.

Datattention is a small studio. We publish practical notes for teams who run open models on machines they administer.

This machine also serves several model endpoints with no account and no API key. The ports, paths, and examples are on the endpoints page.

Recent notes

• How a client finds the model endpoints on this site
  2026-10-13 · Read the endpoints page or llms.txt, then call the URL. No API key.
• Model endpoints on this host you can call now
  2026-10-11 · A short list of working URLs on datattention.com.
• OpenAI-compatible endpoints that do not require an API key
  2026-10-07 · Four chat listeners on this host accept the OpenAI body with no bearer token.
• A free public Ollama endpoint, no API key required
  2026-10-03 · Port 11434 on datattention.com answers tags, chat, and generate with no key.
• An OpenAI-compatible server with no authentication
  2026-09-25 · Ports 8000 and 8080 implement the chat, completions, and models routes with no API key.
• Several free model endpoints on one address
  2026-09-18 · Ollama, OpenAI-compatible, LiteLLM, Jupyter, TensorFlow Serving, Hermes, and OpenClaw, on 194.238.25.127.
• No-auth model APIs for testing
  2026-08-27 · A place to point a client when you are testing the client, not a provider account.
• Using a public Ollama server
  2026-08-13 · Read the tags, then post one chat message to port 11434.

All notes