Two Nvidia data center GPUs, one Ampere and one Volta: 80 GB HBM2e against 32 GB HBM2 and 2.1x the memory bandwidth on the A100.
At a glance
Memory
- A100
- 80 GB
- V100
- 32 GB
2.5x more on A100
Memory bandwidth
- A100
- 1,935 GB/s
- V100
- 900 GB/s
2.1x higher on A100
Cheapest on-demand
- A100
- $0.40 /GPU/hr
- V100
- $0.11 /GPU/hr
3.6x more expensive on A100
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A100 | V100 | Difference |
|---|---|---|---|
| On-demand | $1.75 /GPU/hr from $0.40 | $0.97 /GPU/hr from $0.11 | 45% cheaper on V100 |
| Reserved | $1.63 /GPU/hr from $0.50 (1 mo) | $1.51 /GPU/hr from $0.14 (1 mo) | 8% cheaper on V100 |
| Spot | $1.14 /GPU/hr from $0.20 | $0.43 /GPU/hr from $0.08 | 2.7x more expensive on A100 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. Verify before provisioning. More on how we price.
Price history
A100 vs V100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A100 | V100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e 40 GB on SXM, PCIe | 32 GB HBM2 | 2.5x more on A100 |
| Bandwidth | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 900 GB/s | 2.1x higher on A100 |
| Bus width | 5,120-bit | 4,096-bit | 1.2x wider on A100 |
| Compute · dense | |||
| FP16 / BF16 | 312 TFLOPS | 125 TFLOPS | 2.5x higher on A100 |
| INT8 | 624 TOPS | ||
| FP32 | 19.5 TFLOPS | 15.7 TFLOPS | 1.2x higher on A100 |
| FP64 | 9.7 TFLOPS | 7.8 TFLOPS | 1.2x higher on A100 |
| Platform | |||
| Interconnect | NVLink 600 GB/s | NVLink 300 GB/s | 2x higher on A100 |
| Board power | 300 W | 300 W | Identical |
| Released | Q2 2020 | Q2 2017 | 3 years newer on A100 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP16FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A100 datasheet and V100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A100 /GPU/hr | V100 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.40 | On-Demand $0.11 |
GPU.ai
|
On-Demand $0.54 | On-Demand $0.12 |
Runpod
|
On-Demand $1.00 | On-Demand $0.23 |
Thunder Compute
|
On-Demand $1.09 | -- |
Lium
|
On-Demand $1.23 | -- |
Massed Compute
|
On-Demand $1.35 | -- |
Spheron
|
On-Demand $1.43 | -- |
Packet·ai
|
On-Demand $1.43 | -- |
HyperAI
|
-- | On-Demand $0.14 |
Runcrate
|
-- | On-Demand $2.57 |
Sesterce
|
-- | On-Demand $2.57 |
Geodd
|
-- | On-Demand $0.16 |
TensorDock
|
-- | On-Demand $0.28 |
44 providers list the A100 and 21 the V100. Every listing is on the A100 page and the V100 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
From $1.30 /GPU/hr Compare -
Nvidia RTX 5090
From $0.35 /GPU/hr Compare -
Nvidia RTX 4090
From $0.23 /GPU/hr Compare
Our data for Nvidia A100 was last updated on Sept. 7, 2026, and for Nvidia V100 on Sept. 7, 2026.