NVIDIA · Hopper · H200
141 GB of HBM3e at 4.8 TB/s, built for training, inference, rag.
From $2.89/hracross 10 providers
Memory
141 GB
HBM3e
Bandwidth
4.80 TB/s
FP16 tensor
1979 TFLOPS
FP8 tensor
3958 TFLOPS
Interconnect
NVLink
TDP
700 W
CUDA cores
16,896
Tensor cores
528
| Provider | Type | Spot | Details |
|---|---|---|---|
 RunPod | neocloud | Yes | View |
 Vast.ai | marketplace | Yes | View |
 CoreWeave | neocloud | — | View |
 Lambda | neocloud | — | View |
 Nebius | neocloud | — | View |
 Crusoe | neocloud | — | View |
 Amazon AWS | hyperscaler | Yes | View |
 Google Cloud | hyperscaler | Yes | View |
 Microsoft Azure | hyperscaler | Yes | View |
 Oracle Cloud | hyperscaler | Yes | View |
