B200 vs H100

H100 is 47% cheaper

Comparing the B200 and H100 for cloud rental? The B200 is available from 8 providers starting at $2.14/hr, while the H100 starts at $1.14/hr across 8 providers. Below is a live breakdown of pricing, VRAM, compute throughput, and where to rent each GPU.

B200

VRAM
192 GB
TFLOPS
1125
Cheapest
$2.14/hr
Cheapest deal
Verda
$2.14/hr
per GPU-hour
SKU1B200.30V
RegionFIN-01
TypeSpot
AWSGCPLambdaNebiusOCIRunPod
See all B200 offers

H100

Best price
VRAM
80 GB
TFLOPS
495
Cheapest
$1.14/hr
Cheapest deal
Verda
$1.14/hr
per GPU-hour
SKU1H100.80S.30V
RegionFIN-01
TypeSpot
AWSCudoGCPLambdaNebiusOCI
See all H100 offers

B200 vs H100 at a glance

Spec profile

B200H100
B200 vs H100 spec comparison radar chartVRAMFP16BandwidthValueProviders

Each axis is scaled to the stronger GPU — the outer edge is better.

Value for money

Compute / $
FP16 TFLOPS per $/hr
526
435
VRAM / $
GB of VRAM per $/hr
90 GB
70 GB
B200H100Higher is better value

Specs are manufacturer peak FP16 Tensor figures; real-world throughput varies by workload, precision, and software stack.

B200 vs H100 specs & pricing

SpecificationB200H100
Cheapest price
$2.14/hr
$1.14/hr
VRAM
192 GB
80 GB
FP16 TFLOPS
1125
495
Memory bandwidth
8000 GB/s
3350 GB/s
Release year
2024
2023
Cloud providers
8
8

Which should you choose?

  • H100 is the cheaper option to rent — about 47% less per GPU-hour ($1.14/hr vs $2.14/hr).
  • B200 has more VRAM (192 GB), so it fits larger models and bigger batch sizes without sharding.
  • B200 offers higher FP16 throughput, training and serving faster on compute-bound workloads.

Provider availability

Only B200
Vast.ai
Both GPUs
AWSGCPLambdaNebiusOCIRunPodVerda
Only H100
Cudo

Frequently asked questions

Is the B200 or H100 cheaper to rent?

H100 is currently cheaper, from $1.14/hr versus $2.14/hr for the B200 — roughly 47% less per GPU-hour.

How much VRAM do the B200 and H100 have?

The B200 has 192 GB of VRAM and the H100 has 80 GB. More VRAM lets you serve larger models and longer context windows on a single GPU.

Which is faster, the B200 or H100?

On paper the B200 is faster, with 1125 FP16 TFLOPS versus 495. Real-world speed also depends on memory bandwidth and software stack.

Which cloud providers offer both the B200 and H100?

Both GPUs are available from AWS, GCP, Lambda, Nebius, OCI, RunPod and 1 more. PlanetGPU tracks live B200 and H100 prices across every major cloud.

Live prices come from public provider catalogs and can change quickly. How we collect prices.

Related GPU comparisons