The P100 is newer, with 33% more memory and 3x the bandwidth, and is cheaper right now.
At a glance
Memory
33% more on P100
- K80
- 12 GB
- P100
- 16 GB
Memory bandwidth
3x higher on P100
- K80
- 240 GB/s
- P100
- 732 GB/s
Cheapest on-demand
89% cheaper on P100
- K80
- $0.90 /GPU/hr
- P100
- $0.10 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | K80 | P100 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.90 | $1.39 /GPU/hr from $0.10 | |
| Reserved | -- /GPU/hr from $0.04 (24 mo) | $1.04 /GPU/hr from $0.22 (24 mo) | |
| Spot | No spot listings | -- /GPU/hr from $0.08 |
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. No median for on-demand and reserved on the K80 and spot on the P100: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
K80 vs P100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | K80 | P100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 12 GB GDDR5 | 16 GB HBM2 | 33% more on P100 |
| Bandwidth | 240 GB/s | 732 GB/s | 3x higher on P100 |
| Bus width | 384-bit | 4,096-bit | 11x wider on P100 |
| Compute · dense | |||
| FP16 / BF16 | Not supported | 18.7 TFLOPS | P100 only |
| FP32 | 4.4 TFLOPS | 9.3 TFLOPS | 2.1x higher on P100 |
| FP64 | 1.5 TFLOPS | 4.7 TFLOPS | 3.2x higher on P100 |
| Platform | |||
| Interconnect | PCIe only | NVLink 160 GB/s | NVLink on P100 only |
| Board power | 150 W | 250 W | 67% higher on P100 |
| Released | Q4 2014 | Q2 2016 | 2 years newer on P100 |
| Precision | |||
| Supported formats | FP32FP64 | FP16FP32FP64 | |
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: K80 datasheet and P100 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | K80 | P100 |
|---|---|---|
Database Mart
USA
|
$0.0447 /GPU/hr Reserved | $0.22 /GPU/hr Reserved |
AWS
USA
|
$0.90 /GPU/hr On-demand | -- |
Vast.ai
USA
|
-- | $0.10 /GPU/hr On-demand |
Scaleway
France
|
-- | $1.38 /GPU/hr On-demand |
Oracle Cloud
USA
|
-- | $1.27 /GPU/hr On-demand |
Google Cloud
USA
|
-- | $1.51 /GPU/hr On-demand |
Alibaba Cloud
China
|
-- | $1.55 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
Nvidia V100
32 GB HBM2 · 3.8x the bandwidth of the K80
From $0.09 /GPU/hr Compare -
Nvidia T4
16 GB GDDR6 · 25% more bandwidth than the K80
From $0.10 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 2.6x the bandwidth of the P100
From $0.40 /GPU/hr Compare
Our data for Nvidia K80 was last updated on Sept. 14, 2026, and for Nvidia P100 on Sept. 14, 2026.