The NVIDIA A10 is an enterprise-class GPU built on the Ampere architecture, featuring 24 GB of memory with 600 GB/s of memory bandwidth and a 150 W TDP. It delivers 31.2 TFLOPS of FP32 performance and 125 TFLOPS of FP16 tensor performance. Currently available from 1 provider starting at $1.42/GPU/hour, with a market median of $1.42/GPU/hour across 1 configurations.
Cheapest
$1.420/hr
Runcrate
Median
$1.420/hr
across 1 offerings
Most expensive
$1.420/hr
Runcrate
90-day trend
+71.1%
median rate
Hardware specifications
Same across all providers
Memory
24 GB
FP16 performance
125 TFLOPS
peak
TDP
150 W
Memory bandwidth
600 GB/s
Architecture
Ampere
FP32 performance
31.2 TFLOPS
Brand
NVIDIA
Series
A10
Market price history
Median price across all providers
3 offerings from 1 providers
Sorted by price ascending. Compare configurations side-by-side.
| Provider | Count | vCPU | RAM | Region | Per GPU hour | Total/hr | Action |
|---|---|---|---|---|---|---|---|
| ×1 | 30 | 200 GB | -- | $1.290 | $1.29 | ||
 Sesterce CloudReferral link | ×1 | 30 | 200 GB | -- | $1.419 | $1.42 | |
 RuncrateCheapest | ×1 | 30 | 200 GB |  | $1.420 0.0% 30d | $1.42 | Launch |
See more GPUs like this in
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the A10 cost per hour?
The A10 starts at $1.42 per GPU-hour, with a median of $1.42 across 1 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the A10?
3 providers currently list the A10: Runcrate, Sesterce Cloud, Lambda. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the A10 have?
The A10 comes with 24 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the A10 cheapest?
The lowest on-demand price we currently track for the A10 is $1.42 per GPU-hour at Runcrate. Because providers update pricing and availability frequently, check the live table above before you launch.