Cheapest NVIDIA H100 80GB SXM for LLM inference 70B
80GB VRAM · 1979 TFLOPS FP16 · 80GB min for LLM inference 70B
Best price: $2.29/hr on Vast.ai
on-demand · us-east · verify before purchasing
NVIDIA H100 80GB SXM Prices — 14 offers
14 offers found
— from $2.29/hr
as of Apr 29, 2026, verify on provider site
Some links are affiliate links — we may earn a commission at no cost to you.Details.
| Provider | Price/hr | Configuration | Region | Billing | Availability | Rent |
|---|---|---|---|---|---|---|
| Vast.aicheapest | $2.29/hr | 1x H100 SXM | us-east | per-second | on-demand | Rent → |
| FluidStack | $2.49/hr | 1x H100 SXM5 | us-east | per-minute | on-demand | Rent → |
| Lambda Labs | $2.49/hr | 1x H100 SXM | us-south-1 | per-minute | on-demand | Rent → |
| DataCrunch | $2.59/hr | 1x H100 SXM5 80GB | eu-north | per-minute | on-demand | Rent → |
| Genesis Cloud | $2.69/hr | 1x H100 SXM | us-east | per-minute | on-demand | Rent → |
| Hyperstack | $2.79/hr | 1x H100 SXM5 80GB | uk-london | per-minute | on-demand | Rent → |
| CoreWeave | $2.95/hr | 1x H100 SXM5 | us-east | per-second | on-demand | Rent → |
| Modal | $3.95/hr | 1x H100 SXM | us-east | per-second | on-demand | Rent → |
| RunPod | $3.99/hr | 1x H100 SXM | us-east | per-second | on-demand | Rent → |
| RunPod | $3.99/hr | 1x H100 SXM | us-east | per-second | on-demand | Rent → |
| Fal.ai | $4.50/hr | 1x H100 | us-east | per-hour | on-demand | Rent → |
| Lambda Labs | $19.92/hr | 8x H100 SXM | us-south-1 | per-minute | on-demand | Rent → |
| Paperspace | $1994.00/hr | 1x H100 | us-east-1 | per-hour | on-demand | Rent → |
| Paperspace | $1994.00/hr | 1x H100 | us-east-1 | per-hour | on-demand | Rent → |
Compatibility
FAQ
Is the NVIDIA H100 80GB SXM good for LLM inference 70B?
Yes. LLM inference 70B requires 80GB VRAM; the NVIDIA H100 80GB SXM has 80GB.
What is the cheapest NVIDIA H100 80GB SXM for LLM inference 70B?
Vast.ai at $2.29/hr (on-demand, us-east).
Last refresh: April 29, 2026. Verify on provider site.