Live readiness of the hosted platform, refreshed every 15 seconds from the same endpoint the operators watch (GET /api/v1/status). The figures underneath are what the router actually did, across every workspace.
Readiness of this deployment from GET /api/v1/status.
1.3K metered requests in total; 1K in the last 24 hours.
Success rate
92%
Metered requests answered without a 5xx
Workspaces routing
13
20 signed up
Saved by routing
97%
$6.69 against sending everything to llm-frontier
Targets
24 / 12
In the catalogue / executable here