We launched the t1.micro instance type in 2010, and followed up with the first of the T2 instances (micro, small, and medium) in 2014, more sizes in 2015 (nano) and 2016 (xlarge and 2xlarge), and unlimited bursting last year.
Today we are launching T3 instances in twelve regions. These general-purpose instances are even more cost-effective than the T2 instances, with On-Demand prices that start at $0.0052 per hour ($3.796 per month). If you have workloads that currently run on M4 or M5 instances but don’t need sustained compute power, consider moving them to T3 instances. You can host the workloads at a very low cost while still having access to sustainable high performance when needed (unlimited bursting is enabled by default, making these instances even easier to use than their predecessors).
As is the case with the T1 and the T2, you get a generous and assured baseline amount of processing power and the ability to transparently scale up to full core performance when you need more processing power, for as long as necessary. The instances are powered by custom high frequency Intel® Xeon® Scalable (Skylake) Processors featuring the new Intel® AVX-512 instructions and you can launch them today in seven sizes:
|Name||vCPUs||Baseline Performance / vCPU||Memory||Price / Hour|
|Price / Hour|
The column labeled Baseline Performance indicates the percentage of a single hyperthread’s processing power that is allocated to the instance. Instances accumulate credits when idle and consume them when running. For running instances, credits never expire. For stopped instances, credits are stored for up to 7 days and then they expire. If the average CPU utilization of a T3 instance is lower than the baseline over a 24 hour period, the hourly instance price covers all spikes in usage. If the instance runs at higher CPU utilization for a prolonged period, there will be an additional charge of $0.05 per vCPU-hour. This billing model means that you can choose the T3 instance that has enough memory and vCPUs for your needs, and then count on the bursting to deliver all necessary CPU cycles. This is a unique form of vertical scaling that could very well enable some new types of applications.
T3 instances are powered by the Nitro system. In addition to CPU bursting, they support network and EBS bursting, giving you access to additional throughput when you need it. Network traffic can burst to 5 Gbps for all instance sizes; EBS bursting ranges from 1.5 Gbps to 2.05 Gbps depending on the size of the instance, with corresponding bursts for EBS IOPS.
Like all of our most recent instance types, the T3 instances are HVM only, and must be launched within a Virtual Private Cloud (VPC) using an AMI that includes the Elastic Network Adapter (ENA) driver.
The T3 instances are available in the US East (Ohio), US East (N. Virginia), US West (N. California), US West (Oregon), Canada (Central), Europe (Ireland), Europe (London), Europe (Frankfurt), South America (São Paulo), Asia Pacific (Tokyo), Asia Pacific (Singapore), and Asia Pacific (Sydney) Regions. To learn more, visit the EC2 T3 instance page.