Skip to main content
Cerebrium’s multi-region deployment capability allows you to deploy your apps globally across different continents, taking advantage of co-location for reduced latency and meeting data residency requirements.
Multi-region deployment is currently in beta. Rapid updates and improvements will be made over the next few months to bring full functionality to life. Please reach out on our Discord about features/functionality you would like to see

​
Why Use Multi-Region Deployment

  • Reduced Latency: Deploy closer to users for faster response times and better experience with real-time applications like voice agents and LLMs
  • Data Residency: Meet data protection requirements by keeping sensitive data within specific geographic regions to comply with regulations like GDPR and CCPA
  • High Availability: Ensure fault tolerance and continuous service through geographic redundancy, disaster recovery, and load balancing across multiple regions

​
Available Regions

Cerebrium supports deployment across three major continents with the following regions:

​
United States

  • us-east-1 (N. Virginia) - Default region

​
Europe

  • eu-west-2 (United Kingdom)

​
Asia Pacific

  • ap-south-1 (India) - Coming soon
Additional regions are being evaluated and will be added based on user demand and infrastructure availability. Contact support if you need deployment in a specific region not currently listed.

​
CLI Configuration

You can configure your CLI to work with different regions in two ways: Set a default region for your CLI sessions that will be used for all commands: 
cerebrium region set us-east-1
This will set the default region for commands like listing storage volumes, running applications, and other operations. Alternatively, you can specify the region for individual commands using the --region flag: 
# List storage volumes in a specific region
cerebrium ls --region eu-west-2
The --region flag takes precedence over the default region set with cerebrium region set. This allows you to temporarily use a different region without changing your default configuration.

​
App Deployment

Configure your app’s deployment region using the region parameter in the [cerebrium.hardware] section of your cerebrium.toml file: 
[cerebrium.hardware]
region = "us-east-1"
provider = "aws"
compute = "AMPERE_A10"
cpu = 2
memory = 8.0

​
Pricing

Pricing varies by region based on local infrastructure costs and availability:

​
GPU Availability by Region

GPU availability and pricing vary across regions due to infrastructure constraints and local demand:
GPU ModelUS EastEU WestAP South
HOPPER_H100✅✅✅
AMPERE_A100_40GB✅✅✅
ADA_L40S✅❌❌
ADA_L4✅✅✅
AMPERE_A10✅✅✅
TURING_T4✅✅✅

​
Limitations

  • Each region requires a separate deployment. Apps deployed in one region do not automatically replicate to other regions.
  • Each region has its own isolated persistent storage volume. Data stored in /persistent-storage in one region is not accessible from other regions.