Fleet Analytics

Total tokens · cost per inference · regional coverage

Updated 7:26:52 AM

Active Nodes

501

across all regions

Tokens / hr

85.8M

fleet-wide throughput

Req / sec

1,454.9

real-time aggregate

Cost / 1k tokens

$0.0011

weighted avg, all routes

Cloud Savings

$0.87k

vs cloud-only this hr

Success Rate

98%

fleet-wide p50

Click any two regions to inspect latency & transfer cost between peer nodes

Select 2 regions to inspect the link

Local: 41%

Mesh: 34%

Cloud: 25%

90-day history + 30-day forecast · adjust model offloading policy to see savings impact

Projected monthly (cloud-only)

$0.84

Monthly cost with Local First

$0.24

→

Monthly savings vs cloud-only

$0.60(71%)

Annual projection

$7 saved / yr

Region	Nodes	Tokens/hr	Req/sec	Cost/1k tok	p50 Latency	p99 Latency	Success %
US West	79	21.93M	48.1	$0.00142	80ms	225ms	98.9%
EU Central	44	20.84M	73.8	$0.00119	82ms	189ms	97%
AP East	42	16.68M	288	$0.00092	145ms	253ms	97.1%
SA East	114	14.63M	379.2	$0.00132	147ms	211ms	97.4%
EU West	99	6.49M	281.7	$0.00096	152ms	272ms	99.9%
AP South	38	4.34M	105.7	$0.00071	164ms	343ms	97.9%
US East	85	0.88M	278.4	$0.00116	129ms	220ms	97.5%

Data refreshes every 8 seconds in live mode. All figures are fleet-wide aggregates across all active peer nodes and cloud fallback routes.