Skip to content
// FLEET
us-west-1GB300 · liquid
eu-central-1B300 · liquid
apac-sg-1GB200 · NVL72
me-uae-1VR200 · Rubin
// HOPPER
Available

H100 SXM

The proven Hopper workhorse for inference and fine-tuning.

Best for
inferencefine-tuning
Available in 5 regions
us-west-1us-east-1eu-central-1apac-sg-1ap-ph-1
Pricing

$2.49/GPU-hr

Architecture
Hopper
Form factor
SXM
Memory
80 GB HBM3
Bandwidth
3.35 TB/s
NVLink
Gen 4
Board power
700 W
// SOFTWARE STACK
CUDANVLinkTensorRT-LLMvLLMSGLangNVIDIA DynamoNVFP4KV-cachespeculative decoding