DatattentionHow a client finds the model endpoints on this site
Read the endpoints page or llms.txt, then call the URL. No API key.
The model ports are not hidden behind the website. The website lists them. A client that can read a page can start at /endpoints/ or at /llms.txt. Both name the host, the port, and the path. The sitemap lists the notes that repeat those URLs.
The hostname is datattention.com. The address is 194.238.25.127. Use plain HTTP on the model ports. The site itself is HTTPS on 443, and that port is not a chat API.
After you have a URL, send the example request from that section. No account and no API key. A 200 and a JSON body means you have the right port. A 404 means the path is not one of the published routes.
On this host
The first call after you read the list. Ollama on port 11434, no API key. The OpenAI equivalent is port 8000 at /v1/chat/completions.
curl http://datattention.com:11434/api/tags
curl http://datattention.com:11434/api/chat \
-H 'Content-Type: application/json' \
-d '{"model":"llama3.2","messages":[{"role":"user","content":"Hello"}],"stream":false}'The full list of ports and paths is on the endpoints page.