Status
A probe checks the whole path every 30 seconds; real traffic shows how fast answers start. Numbers are aggregated: no key, address or prompt appears here.
Checking…
vllm-sr/auto
Uptime · 24 hours
—
Uptime · 7 days
—
Uptime · 30 days
—
History
now
Speed
First token · p50 / p90
—
Server errors · 15 min
—
5xx share of answered requests
Last probe
—
Usage
Hourly activity across the API. All times are UTC.
Requests
—
Last 12 hours
Total tokens
—
Input + output · last 12 hours
Peak requests / hour
—
Last 12 hours
Keys created · all time
—
Requests
per hourLoading hourly requests…
Total tokens
input + output, per hourLoading hourly tokens…
The current hour is still in progress. Hover, tap or use arrow keys to inspect an hour.
Loading usage…
Routed today UTC
Loading routed requests…