The NVIDIA A16 is an enterprise-class GPU built on the Ampere architecture, featuring 16 GB of memory. Currently available from 3 providers starting at $0.48/GPU/hour, with a market median of $0.52/GPU/hour across 16 configurations.
Cheapest
$0.477/hr
Vultr
Median
$0.519/hr
across 16 offerings
Most expensive
$0.564/hr
Sesterce Cloud
90-day trend
-7.3%
median rate
Hardware specifications
Same across all providers
Memory
16 GB
Architecture
Ampere
Brand
NVIDIA
Series
A16
Market price history
Median price across all providers
3 offerings from 3 providers
Sorted by price ascending. Compare configurations side-by-side.
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the A16 cost per hour?
The A16 starts at $0.48 per GPU-hour, with a median of $0.52 across 16 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the A16?
3 providers currently list the A16: Runcrate, Sesterce Cloud, Vultr. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the A16 have?
The A16 comes with 16 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the A16 cheapest?
The lowest on-demand price we currently track for the A16 is $0.48 per GPU-hour at Vultr. Because providers update pricing and availability frequently, check the live table above before you launch.