OCPI·LIVE
H100from $1.95H100from $1.66H100from $2.59H200from $3.00H200from $3.79A100from $1.00A100from $1.99A100from $1.35A100from $1.35B200from $3.74B300from $6.94L40Sfrom $0.69RTX 4090from $0.34RTX 5090from $0.65H100from $1.95H100from $1.66H100from $2.59H200from $3.00H200from $3.79A100from $1.00A100from $1.99A100from $1.35A100from $1.35B200from $3.74B300from $6.94L40Sfrom $0.69RTX 4090from $0.34RTX 5090from $0.65
Index / Compare
Cloud GPU Price Comparison

B300 vs H100

B300 SXM 288GB vs H100 SXM5 80GB — current cloud rental cost per hour, normalized to USD per GPU across providers. H100 SXM5 80GB is currently the cheaper option — about 47% less on the headline comparison metric.

B300 SXM 288GB
NVIDIA Blackwell Ultra · SXM
$7.40/GPU/hr
single index provider · not a median
range $6.94–$16.82 · 4 providers
cheapest: RunPod $6.94
↗ Full B300 SXM 288GB prices
H100 SXM5 80GB
NVIDIA Hopper · SXM
$3.95/GPU/hr
index median · 2 providers
range $1.95–$5.97 · 5 providers
cheapest: Shadeform $1.95
↗ Full H100 SXM5 80GB prices

B300 vs H100: memory and workload context

spec context · not a performance benchmark
ContextB300 SXM 288GBH100 SXM5 80GB
ArchitectureNVIDIA Blackwell UltraNVIDIA Hopper
Memory288GB HBM3e80GB HBM3
Common workloadsfrontier model training, reasoning inference, memory-intensive AI workloadslarge model training, high-throughput inference, distributed fine-tuning
Price interpretationB300 is a distinct 288GB Blackwell Ultra GPU. It is not combined with GB300 systems, and early cloud coverage should be read with the provider count.H100 SXM is usually the premium H100 shape, with stronger node-level bandwidth than PCIe deployments.

B300 vs H100 price table

USD per GPU per hour · live provider data
MetricB300 SXM 288GBH100 SXM5 80GB
Index median$7.40/hr$3.95/hr
Community marketplace median$6.94/hr$2.69/hr
Cheapest current row$6.94 · RunPod$1.95 · Shadeform
Provider coverage4 providers · 18 listings5 providers · 44 listings
Best use of this pageUse this as a price comparison and sourcing snapshot. Performance, memory size, software support, and availability still need to be checked with the provider.
“

Listed price ≠ transaction price

These are published rates, normalized per GPU per hour and labeled by billing mode. The index median uses eligible reliable-tier providers only. Read the methodology →