EC2 instances
There are a variety of instance types to choose from when creating a Cortex cluster. If you are unsure about which instance to pick, review these options as a starting point.
This is not a comprehensive guide so please refer to the AWS's documentation for more information.
Note: you may have limited (or no) access to certain instance types. To check your limits, click here, set your region in the upper right, and type "on-demand" in the search box. You can request a limit by selecting an instance family and clicking "Request limit increase" in the upper right. Note that the limits are vCPU-based no matter the instance type (e.g. to run 4 g4dn.xlarge instances, you will need a 16 vCPU limit for G instances).
Instance Type | CPU | Memory | GPU Memory | Starting price per hour* | Notes |
​T3​ | low | low | - | $0.0416 (t3.medium) | good for dev clusters |
​M5​ | medium | medium | - | $0.096 (m5.large) | standard cpu-based |
​C5​ | high | medium | - | $0.085 (c5.large) | high cpu |
​R5​ | medium | high | - | $0.126 (r5.large) | high memory |
​G4​ | high | high | ~15GB (g4dn.xlarge) | $0.526 (g4dn.xlarge) | standard gpu-based |
​P2​ | high | very high | ~12GB (p2.xlarge) | $0.90 (p2.xlarge) | high host memory gpu-based |
​Inf1​ | high | medium | ~8GB (inf1.xlarge) | $0.368 (inf1.xlarge) | very good price/performance ratio |
* on-demand pricing for the US West (Oregon) AWS region.