Tesla V100 vs A100
Tesla V100 starts at $0.17/GPU-hour on-demand; A100 starts at $0.89/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. Peak compute figures do not establish application speed.
80.9% cheaper at Tesla V100.
updated 2026-10-06. Price alone does not establish equivalent capacity or performance.
Tesla V100
A100
Spec sheet
| Tesla V100 | A100 | |
|---|---|---|
| Spec variant | Tesla V100 (unspecified) | A100 SXM 40GB |
| Architecture | Volta | Ampere |
| VRAM (spec variant) | 16 GB | 40 GB |
| FP16 TFLOPS (dense) | 125 | 312 |
| Memory bandwidth | 900 GB/s | 1555 GB/s |
| TDP | 300 W | 400 W |
| Interconnect | NVLink 300GB/s | NVLink 600GB/s |
| Launched | 2017 | 2020 |
What they cost to rent (2026-10-06)
| Tesla V100 | A100 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.17 | $0.89 |
| Cheapest spot/community $/hr | $0.19 | $0.679 |
| Cheapest source | TensorDock | Jarvislabs |
| Providers offering it | 6 | 22 |
Lowest recorded on-demand rate per configuration; highlighted = cheaper. Spot/marketplace tiers shown on the individual pages.
FAQ
Tesla V100 is cheaper: the Tesla V100 rents from $0.17 per GPU-hour and the A100 from $0.89 on-demand, updated 2026-10-06.
The largest recorded Tesla V100 variant has 16 GB and the largest A100 variant has 80 GB. Other variants may have less memory. The A100 has more.
Compare more rental options: the screener · price movers · methodology.