Regions & Availability

machine.dev runs on AWS infrastructure across 6 regions. Pick regions for data locality, compliance, or cost. If you don’t specify, machine.dev considers supported regions and ranks available options using your team’s tiering strategy.

Available regions

GPU availability by region

Not every GPU type is available in every region. CPU runners (X64 and ARM64) are available everywhere.

AI accelerators (Trainium, Inferentia2) are currently US-only. Trainium and Inferentia2 run in us-east-1, us-east-2, and us-west-2. Inferentia2 is also available in ap-southeast-2.

AWS regional capacity changes over time. See the pricing page for the live availability and best-rate-by-region view.

Specifying regions

Pass regions= with a comma-separated list. This restricts placement to the listed regions. Available options are ranked using your team’s tiering strategy:

runs-on: machine/gpu=l4/regions=us-east-1,us-east-2

How auto-selection works

When you don’t specify regions=, machine.dev considers supported regions for the requested runner. When you list regions, it considers only those regions. For spot, Settings → General → Intelligent Tiering Strategy controls ranking:

The reliability signal is historical, not a guarantee that a runner will avoid interruption. If spot capacity is unavailable, On-Demand Fallback determines whether machine.dev can launch an on-demand runner instead. See Spot runners & savings.

Allowing multiple regions gives machine.dev more capacity and pricing options. Pin one region when you need data residency or locality.

Compliance and data residency

Need a region we don’t support?

Email hello@machine.dev to request a region. New regions are added based on customer demand.

Next steps

• Configuration options: every label for runs-on
• GPU Runners: GPU types, configurations, prices
• Cost Optimization: using region selection to save money