Z
Zyeon UI

Token Latency · Zyeon UI

A four-state LLM serving-latency scatter: time to first token against time per output token for every request, nearest-rank p50/p95 crosshairs, an inclusive budget crosshair that cuts the plane into four filterable zones, and queue/prefill/decode phase bars for the median and p95 requests.

npx shadcn@latest add @zyeon/chart-token-latency
Preview Token Latency on Zyeon UI's site (opens in a new tab)

Token Latency is part of Zyeon UI's licensed catalog

Sign in or get a license at Zyeon UI to see its source and install it.