Status

Loading…

← Demo · numbers are measured on this server, from arrival to token sent

Requests per minute

Last 60 minutes, by outcome

Served Busy (429) Server error (5xx)

Latency

Per minute, successful requests; time to first token includes the wait for a slot

First token p50 First token p95 Whole request p95 SLO

Load

Engine snapshots every 5 s

Busy slots Waiting in queue Slots
Show the last hour as a table