Two Nvidia data center GPUs, one Grace Blackwell and one Volta: 186 GB HBM3e against 32 GB HBM2 and 8.9x the memory bandwidth on the GB200.
At a glance
Updated 6 minutes ago- Memory
- 186 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- $10.50 /GPU/hr
- 8 providers
- Memory
- 32 GB
- HBM2
- Memory bandwidth
- 900 GB/s
- From
- $0.14 /GPU/hr
- 19 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | GB200 | V100 | Difference |
|---|---|---|---|
| On-demand | $10.50 | $0.14 | 75x more expensive on GB200 |
| Spot | $27.04 | $0.09 | 318x more expensive on GB200 |
| Reserved | $10.58 | $0.13 | 83x more expensive on GB200 |
| Median | $16.00 | $1.57 | 10x more expensive on GB200 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
GB200 vs V100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GB200 | V100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 186 GB HBM3e | 32 GB HBM2 | 5.8x more on GB200 |
| Bandwidth | 8,000 GB/s | 900 GB/s | 8.9x higher on GB200 |
| Bus width | 4,096-bit | ||
| Compute · dense | |||
| FP4 | 10,000 TFLOPS | Not supported | GB200 only |
| FP8 | 5,000 TFLOPS | Not supported | GB200 only |
| FP16 / BF16 | 2,500 TFLOPS | 125 TFLOPS | 20x higher on GB200 |
| INT8 | 5,000 TOPS | ||
| FP32 | 80 TFLOPS | 15.7 TFLOPS | 5.1x higher on GB200 |
| FP64 | 40 TFLOPS | 7.8 TFLOPS | 5.1x higher on GB200 |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 300 GB/s | 6x higher on GB200 |
| Board power | 1,200 W | 300 W | 4x higher on GB200 |
| Released | Q1 2024 | Q2 2017 | 7 years newer on GB200 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | 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: GB200 datasheet and V100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | GB200 /GPU/hr | V100 /GPU/hr |
|---|---|---|
CoreWeave
|
On-Demand $10.50 | -- |
Oracle Cloud
|
On-Demand $16.00 | -- |
Azure
|
On-Demand $27.04 | -- |
AWS
|
Reservation $10.58 | -- |
CUDO
|
Custom on request | -- |
Canopy Wave
|
Custom on request | -- |
Nebius
|
Custom on request | -- |
Together AI
|
Custom on request | -- |
HyperAI
|
-- | On-Demand $0.14 |
Verda
|
-- | On-Demand $0.17 |
Runcrate
|
-- | On-Demand $2.57 |
Sesterce
|
-- | On-Demand $2.57 |
Geodd
|
-- | On-Demand $0.16 |
TensorDock
|
-- | On-Demand $0.28 |
Cyfuture AI
|
-- | On-Demand $0.55 |
OVH
|
-- | On-Demand $0.77 |
8 providers list the GB200 and 19 the V100. Every listing is on the GB200 page and the V100 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GB200 was last updated on Sept. 7, 2026, and for Nvidia V100 on Sept. 7, 2026.