DatattentionAn OpenAI-compatible server with no authentication
Ports 8000 and 8080 implement the chat, completions, and models routes with no API key.
An OpenAI-compatible server is a claim about routes. This one implements GET /v1/models, GET /v1/models/{id}, POST /v1/chat/completions, POST /v1/completions, and POST /v1/embeddings. Health is GET /health and GET /v1/health. That is the surface vLLM and llama.cpp clients already know.
No authentication means the request is complete without an Authorization header. Do not invent a key. GET /v1/models lists gpt-4o-mini, claude-opus-5-5, claude-fable-5-1, and gpt-6-astra. The server echoes the name you send.
Two ports on this host serve that surface, 8000 and 8080. Use either. Streaming is available by setting stream to true, as the streaming note describes.
On this host
No API key. Port 8080 is the second listener, for a client that is already aimed there.
curl http://datattention.com:8080/v1/models
curl http://datattention.com:8080/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.