Compute close to major cities.
Deploy compute, storage, and databases in 30+ metro areas. Single-digit millisecond latency to end users in that city.
30+
Metros
< 5 ms
Latency
Full stack
Services
VPC peered
Connect
Closer to users.
30+ metros with sub-5ms latency.
30+ metros
Local Zones in Los Angeles, Boston, Miami, Houston, and 25+ more.
Sub-5ms latency
Single-digit ms to users in that metropolitan area.
Full services
Compute, block storage, databases, and load balancers available.
VPC extension
Extend your VPC to local zones. Same security groups.
Same APIs
Use the same APIs and tools as regular regions.
GPU instances
GPU compute for local rendering and inference.
Getting started
Launch your first instance in three steps. CLI, console, or API — your choice.
ur compute local-zone enable \
--zone=us-east-1-bos-1aLocal Zone patterns.
Media creation and game streaming.
Suggested configuration
GPU · Low-latency · Local
Estimate your costs
Create detailed configurations to see exactly how much your architecture will cost. Pay for what you use, down to the second.
Configuration 1
Platform & Architecture
Local Resources
Storage
Cost Optimization
Cost details
Low-latency compute in metropolitan areas.
Works seamlessly with
Frequently asked questions
Closer to users.
30+ metros. Sub-5ms. Full services.