Health Status

Live Connections

All currently active proxy connections with queue state, streaming mode, and live metrics.

Backends

Inspect backend status, load, errors, and concurrency settings in one place.

Backend Status Load Models Metrics Last Error Controls

Chat Debugger

Chat directly through the proxy, similar to the built-in llama.cpp frontend, including live tokens, sampler parameters, and raw responses.

Request JSON

// request appears here

Response / Stream

// response appears here

Recent Requests

Live history with queue time, target backend, and outcome.