Google Compute Engine’s instances can be moved to nearby hosts while active—even
while under extreme load—complete with their working SSD storage (up to 1.5 TB).
Since your VMs don’t need to be rebooted for host software updates
or other standard operational tasks,
uptimes are superb.
This ensures predictable performance across all the different parts of your
application. Learn more
We’ve re-invented the way you pay for cloud. Innovations like per-minute-billing,
sustained-use discounts that offer optimal pricing without locking you into
potentially obsolescent gear, custom machine types (see below) and special pricing
for particular use cases combine to give you the best price-performance available
from any cloud computing provider. You can use our detailed pricing calculator
to model your savings in switching to Google Cloud Platform.
Custom Machine Types
Any size machine, as long as it’s a power of 2? Not on Cloud Platform.
We let you configure the right combination of memory & virtual CPU for your
workload, so you no longer have to overprovision to fit your vendor’s rate card,
which means more savings for you, potentially up to 50% more price/performance
efficient, depending on your workload. Learn more
Sub-second Archive Restore
Google Cloud Storage Nearline delivers sub-second data availability and
provides high throughput for prompt restoration of data. In fact, it’s fast enough
that many customers simply use it as their only storage tier. Competing systems
take 4-5 hours to do the same data archiving tasks, offer substantially lower throughput, and often
charge confusing and expensive fees for restore. Ours fees are simple: 1 penny
per GB/month to store, 1 penny per GB to restore. Learn more
Global load balancers that scale to 1 million+ users instantly.
Our built-in load balancer is part of a worldwide distributed system for delivering
customers to infrastructure, the same system that supports Google products like
Maps, Gmail, and Search. Its autoscaling capabilities are designed to tolerate extreme spikes in traffic, and
easily scale from no traffic to millions of requests per second, in seconds. This
improves the performance of your applications: every user, no matter how many of
them show up at once, will make it through to your stack.
Faster boot times
Compute Engine instances boot in the range of 40-50 seconds, roughly 1/5 of
the time required by competing clouds. This means you can grow your application’s
serving capacity very rapidly in response to incoming traffic, just like
we do for our own applications. Learn more
680,000 IOPS sustained Local SSD read rate
All but the smallest flavors of Compute Engine can mount up to 1.5TB of Local SSD capable
of 680k of sustained read performance. Competing systems max out at less than half
that speed for nearly four times the cost, and are only available on certain
instance sizes. Faster IOPS makes everything in your app faster,
and lets you handle more users per instance. Learn more
Google grade security
Deploy on an infrastructure protected by more than 500 top experts in information, application, and network security. The Google security model is an end-to-end process, built on over 15 years of experience focused on keeping customers safe on Google applications like Gmail and Google Apps. With Cloud Platform your applications and data take advantage of the same pervasive security model. Learn more
Global network of data centers
The same infrastructure that runs Google apps is available to you on Cloud Platform. Google’s global network footprint, with over 75 points-of-presence across more than 33 countries, ensures you receive the same low latency and responsiveness customers expect from Google's own services. Recognized as some of the most energy efficient and secure in the world, Google’s decade of data center innovation is immediately available to you.