If your Google Cloud Platform workloads over Cloud Interconnect – Dedicated require 5 milliseconds of round-trip latency between VM instances in the specified region and its associated interconnect locations, refer to the Locations table in this document.
The pricing for low-latency locations is the same as for all other locations.
If your workloads don't require low-latency connectivity, you can use any of our Colocation facilities locations.
Requirements and recommendations
For Google Cloud Interconnect - Dedicated your network must physically meet Google's network in a supported colocation facility, also known as an interconnect location), where a vendor, the colocation facility provider, provisions a circuit between your network and a Google Edge Point of Presence. For more information, see the Cloud Interconnect Overview.
The Region served as listed in the table below indicates the regions in which you can
create VLAN attachments,
which affects latency and egress costs. For example, if you
have VM instances in region
us-east4 (Virginia), you might create a dedicated
connection in Ashburn and then create an interconnect attachment (VLAN) in
That way, your traffic doesn't have to travel far to move between your VM instances and
the dedicated connection, resulting in lower latency than, for example, creating
a dedicated connection and an interconnect attachment in Europe.
Also, it's more cost effective to create interconnect attachments in the same regions as your VM instances because you don't have to pay inter-region egress costs when VM instances send traffic to your on-premises network.
Other GCP location options
- Network edge locations allow you to peer with GCP and connect to GCP services. Peering does not require Cloud Interconnect.
- Cloud CDN locations use Google's globally distributed edge points of presence to cache HTTP(S) load balanced content close to your users. Caching content at the edges of Google's network provides faster delivery of content to your users while reducing serving costs.
The following table lists low-latency locations where you can create dedicated
connections. The locations are organized by the GCP regions served, metropolitan
area, and then by metropolitan
availability zone. The name
of each location indicates its metropolitan availability zone, such as the
You can also use the console or gcloud command-line tool to list locations.
|Region served||Metropolitan area||Interconnect location name with < 5 ms to region||Facility provider|
||Ashburn||iad-zone1-1||Equinix Ashburn (DC1-DC11)|
|Ashburn||iad-zone2-1||Equinix Ashburn (DC1-DC11)|
||Los Angeles||lax-zone1-8||Equinix Los Angeles (LA1)|
|Los Angeles||lax-zone2-19||CoreSite - LA1 - One Wilshire|
||London||lhr-zone1-47||Global Switch (London 2)|
|London||lhr-zone2-47||Global Switch (London 2)|
|London||lhr-zone1-832||Equinix London Slough (LD5-LD6)|
|London||lhr-zone2-832||Equinix London Slough (LD5-LD6)|
|Frankfurt||fra-zone1-277||e-shelter Frankfurt (FRA1)|
|Frankfurt||fra-zone1-683||Equinix Frankfurt West (FR4)|
|Frankfurt||fra-zone2-277||e-shelter Frankfurt (FRA1)|
|Frankfurt||fra-zone2-683||Equinix Frankfurt West (FR4)|
||Amsterdam||ams-zone1-1236||Equinix Amsterdam Schepenbergweg (AM5) (formerly Telecity AMS5)|
|Amsterdam||ams-zone2-1320||Equinix Amsterdam (AM3)|
||Zurich||zrh-zone1-81||Interxion Zurich / Glattbrugg|
||Hong Kong||hkg-zone1-225||MEGA-i (iAdvantage Hong Kong)|
|Hong Kong||hkg-zone2-1118||Equinix Hong Kong (HK2)|
|Tokyo||nrt-zone1-452||Equinix Tokyo (TY2)|
|Tokyo||nrt-zone2-452||Equinix Tokyo (TY2)|
||Singapore||sin-zone1-388||Global Switch Singapore|
|Singapore||sin-zone2-2260||Equinix Singapore (SG3)|
|Mumbai||bom-zone2-554||Tata Mumbai IDC|
|Sydney||syd-zone2-1605||Equinix Sydney (SY3)|