A100 vs A40
A100 starts at $0.89/GPU-hour on-demand; A40 starts at $0.59/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. GPU spec numbers are not benchmarks.
33.7% cheaper at A40.
updated 2026-10-12. Price alone does not establish equivalent capacity or performance.
A100
A40
Spec sheet
| A100 | A40 | |
|---|---|---|
| Spec variant | A100 SXM 40GB | A40 |
| Architecture | Ampere | Ampere |
| VRAM (spec variant) | 40 GB | 48 GB |
| FP16 TFLOPS (dense) | 312 | 150 |
| Memory bandwidth | 1555 GB/s | 696 GB/s |
| TDP | 400 W | 300 W |
| Interconnect | NVLink 600GB/s | NVLink 112.5GB/s |
| Launched | 2020 | 2020 |
Rental price per manufacturer-rated FP16 compute: A100 $2.85 per PFLOP-hour vs A40 $3.93. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). This uses A100 SXM 40GB and A40, whose datasheets may differ from the variants above. It is not measured job throughput. Specs: A100 manufacturer, A40 manufacturer.
What they cost to rent (2026-10-12)
| A100 | A40 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.89 | $0.59 |
| Cheapest spot/community $/hr | $0.679 | – |
| Cheapest source | Jarvislabs | RunPod |
| Providers offering it | 22 | 2 |
Cheapest on-demand rate; the cheaper one is highlighted. Spot/marketplace tiers shown on the individual pages.
FAQ
A40 is cheaper: the A100 rents from $0.89 per GPU-hour and the A40 from $0.59 on-demand, updated 2026-10-12.
The largest recorded A100 variant has 80 GB and the largest A40 variant has 48 GB. Other variants may have less memory. The A100 has more.
Compare more rental options: the screener · price movers · methodology.