Two Nvidia data center GPUs, one Blackwell and one Hopper: 180 GB HBM3e against 80 GB HBM3 and 2.3x the memory bandwidth on the B200.
At a glance
Memory
- B200
- 180 GB
- H100
- 80 GB
2.2x more on B200
Memory bandwidth
- B200
- 7.70 TB/s
- H100
- 3.35 TB/s
2.3x higher on B200
Cheapest on-demand
- B200
- $3.75 /GPU/hr
- H100
- $1.50 /GPU/hr
2.5x more expensive on B200
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | B200 | H100 | Difference |
|---|---|---|---|
| On-demand | $6.79 /GPU/hr from $3.75 | $3.39 /GPU/hr from $1.50 | 2x more expensive on B200 |
| Reserved | $5.10 /GPU/hr from $3.75 | $3.16 /GPU/hr from $1.53 (1 mo) | 38% cheaper on H100 |
| Spot | $4.22 /GPU/hr from $3.12 | $2.15 /GPU/hr from $0.14 | 49% cheaper on H100 |
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
B200 vs H100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B200 | H100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 180 GB HBM3e | 80 GB HBM3 94 GB on NVL | 2.2x more on B200 |
| Bandwidth | 7,700 GB/s | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 2.3x higher on B200 |
| Bus width | 5,120-bit | ||
| Compute · dense | |||
| FP4 | 9,000 TFLOPS | Not supported | B200 only |
| FP8 | 4,500 TFLOPS | 1,979 TFLOPS | 2.3x higher on B200 |
| FP16 / BF16 | 2,250 TFLOPS | 989.5 TFLOPS | 2.3x higher on B200 |
| INT8 | 4,500 TOPS | 1,979 TOPS | 2.3x higher on B200 |
| FP32 | 75 TFLOPS | 67 TFLOPS | 1.1x higher on B200 |
| FP64 | 37 TFLOPS | 34 TFLOPS | 1.1x higher on B200 |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | 2x higher on B200 |
| Board power | 1,000 W | 700 W | 1.4x higher on B200 |
| Released | Q1 2024 | Q3 2022 | 2 years newer on B200 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
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: B200 datasheet and H100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B200 /GPU/hr | H100 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $5.50 | On-Demand $1.50 |
GPU.ai
|
On-Demand $5.40 | On-Demand $2.00 |
Vast.ai
|
On-Demand $6.88 | On-Demand $2.00 |
Packet·ai
|
On-Demand $3.75 | -- |
Runpod
|
On-Demand $6.79 | -- |
Spheron
|
On-Demand $7.20 | -- |
Oblivus
|
On-Demand $8.40 | -- |
EmpirioLabs AI
|
On-Demand $9.00 | -- |
HyperAI
|
-- | On-Demand $1.80 |
Koyeb
|
-- | On-Demand $2.50 |
Massed Compute
|
-- | On-Demand $2.73 |
Runcrate
|
-- | On-Demand $2.75 |
Lyceum
|
-- | On-Demand $2.79 |
35 providers list the B200 and 53 the H100. Every listing is on the B200 page and the H100 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B200 was last updated on Sept. 7, 2026, and for Nvidia H100 on Sept. 7, 2026.