Network

38 points of presence, 41 Tbps, one policy.

Every PoP runs the same stack. Capacity is provisioned per region with headroom for peak events, and health is measured from three independent probes.

38points of presence
41 Tbpsglobal capacity
99.99%edge availability
22 msmedian TTFB

Coverage

Where we are

Internal RTT is the median round trip from the PoP to the nearest backbone exchange.

Europe

Point of presenceCodeInternal RTT
HelsinkiFI10 ms
WarsawPL11 ms
FrankfurtDE9 ms
AmsterdamNL10 ms
ParisFR11 ms
LondonGB12 ms
RigaLV12 ms
StockholmSE10 ms
MadridES14 ms
MilanIT13 ms

North America

Point of presenceCodeInternal RTT
AshburnUS8 ms
ChicagoUS9 ms
DallasUS11 ms
SeattleUS10 ms
Los AngelesUS12 ms
TorontoCA10 ms
MontrealCA11 ms
MiamiUS13 ms

South America

Point of presenceCodeInternal RTT
São PauloBR16 ms
SantiagoCL18 ms
BogotáCO19 ms

Asia Pacific

Point of presenceCodeInternal RTT
SingaporeSG15 ms
TokyoJP14 ms
MumbaiIN17 ms
Hong KongHK16 ms
SeoulKR15 ms
SydneyAU18 ms
AucklandNZ21 ms

Middle East & Africa

Point of presenceCodeInternal RTT
DubaiAE17 ms
Tel AvivIL18 ms
JohannesburgZA21 ms
NairobiKE23 ms

Resilience

Failure is a routing event, not an outage

Each PoP has at least two upstreams on separate paths and a local cache that can serve stale content for 30 seconds during origin trouble. Failover is health-driven, with a 3-strike policy and a 10-second hold-down.

  • N+1 capacity in every region
  • Anycast withdrawal under 5 s
  • Stale-while-revalidate by default
  • Quarterly game days, published post-mortems
Current status
99.997%trailing 90-day availability
4 minmedian time to detect
18 minmedian time to mitigate
0customer-visible incidents in Q3

Put your next deployment closer to users.

14-day trial, no card, full network. Migration help included.