DatattentionA public LiteLLM proxy with open access
Port 4000 on this host speaks OpenAI chat and does not require a key.
LiteLLM is a proxy. Applications send it OpenAI-shaped requests, and it forwards them. The port operators remember is 4000. The route applications remember is POST /v1/chat/completions. GET /v1/models is how you see the name the proxy is advertising.
A proxy usually holds upstream keys in its own config. Callers of an open proxy do not. If there is no master key on the proxy, the caller omits Authorization. That is the setup on this host.
Use the proxy URL when you want one OpenAI base URL that is not the Ollama port and not ports 8000 or 8080. The JSON does not change between them.
On this host
The open proxy is http://datattention.com:4000. No API key. GET /v1/models lists gpt-4o-mini, claude-opus-5-5, claude-fable-5-1, and gpt-6-astra.
curl http://datattention.com:4000/v1/models
curl http://datattention.com:4000/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.