← GPU cloud (on-demand)
Amazon Web Services
EC2 p5 (H100 SXM ×8), per GPU
Hyperscaler H100 nodes; price shown per GPU. Sample entry.
Capabilities, explained
What this API can do, and what each capability means for your project.
GPU
H100 SXM
The GPU model. Newer generations are faster per dollar for large models.
VRAM
80 GB
Memory per GPU. A 70B-parameter model needs ~140 GB in 16-bit, or ~40 GB quantised.
Interconnect
infiniband
How fast GPUs talk to each other; matters for multi-GPU training.
Regions
us, eu, asia
Where the hardware is located (latency, data residency).
Per-second billing
Yes
You pay only for the seconds used rather than full hours.
Price history
Only one price recorded so far. The chart appears once the price changes.