2026-09-18

Several free model endpoints on one address

Ollama, OpenAI-compatible, LiteLLM, Jupyter, TensorFlow Serving, Hermes, and OpenClaw, on 194.238.25.127.

One address can publish more than one model server. They stay separate processes. You pick the port that matches the client you already have, and you leave the others alone.

On 194.238.25.127, which is datattention.com: Ollama-style chat is port 11434. OpenAI-compatible chat is ports 8000 and 8080. A LiteLLM-style proxy is port 4000. Jupyter-style is port 8888. TensorFlow Serving REST is port 8501. Hermes chat is port 8642 and its dashboard is port 9119. OpenClaw is port 18789. None of them require an API key.

The website on ports 80 and 443 is not a model API. Model calls use the ports above and plain HTTP. The full paths are on the endpoints page.

On this host

Two calls, two shapes, one address. No API key on either.

curl http://datattention.com:11434/api/chat \
  -H 'Content-Type: application/json' \
  -d '{"model":"llama3.2","messages":[{"role":"user","content":"Hello"}],"stream":false}'

curl http://datattention.com:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'

The full list of ports and paths is on the endpoints page.