Cheapest NVIDIA A100 80GB SXM for LLM inference 70B
80GB VRAM · 312 TFLOPS FP16 · 80GB min for LLM inference 70B
Best price: $1.15/hr on Paperspace
on-demand · us-east-1 · verify before purchasing
NVIDIA A100 80GB SXM Prices — 13 offers
13 offers found
— from $1.15/hr
as of Oct 19, 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 |
|---|---|---|---|---|---|---|
| Paperspacecheapest | $1.15/hr | 1x A100-80G | us-east-1 | per-hour | on-demand | Rent → |
| Paperspace | $1.15/hr | 1x A100-80G | us-east-1 | per-hour | on-demand | Rent → |
| RunPod | $1.79/hr | 1x A100 SXM | us-east | per-second | on-demand | Rent → |
| RunPod | $1.79/hr | 1x A100 SXM | us-east | per-second | on-demand | Rent → |
| FluidStack | $1.85/hr | 1x A100 SXM 80GB | us-east | per-minute | on-demand | Rent → |
| DataCrunch | $1.89/hr | 1x A100 SXM4 80GB | eu-north | per-minute | on-demand | Rent → |
| Hyperstack | $2.06/hr | 1x A100 SXM4 80GB | uk-london | per-minute | on-demand | Rent → |
| CoreWeave | $2.21/hr | 1x A100 SXM4 80GB | us-east | per-second | on-demand | Rent → |
| Lambda Labs | $2.21/hr | 1x A100 SXM | us-west-2 | per-minute | on-demand | Rent → |
| Modal | $3.72/hr | 1x A100 SXM | us-east | per-second | on-demand | Rent → |
| Lambda Labs | $17.68/hr | 8x A100 SXM | us-west-2 | per-minute | on-demand | Rent → |
| Paperspace | $1994.00/hr | 1x A100 | us-east-1 | per-hour | on-demand | Rent → |
| Paperspace | $1994.00/hr | 1x A100 | us-east-1 | per-hour | on-demand | Rent → |
Compatibility
FAQ
Is the NVIDIA A100 80GB SXM good for LLM inference 70B?
Yes. LLM inference 70B requires 80GB VRAM; the NVIDIA A100 80GB SXM has 80GB.
What is the cheapest NVIDIA A100 80GB SXM for LLM inference 70B?
Paperspace at $1.15/hr (on-demand, us-east-1).
Last refresh: October 19, 2026. Verify on provider site.