A100 vs GH200
A100 starts at $0.89/GPU-hour on-demand; GH200 starts at $2.29/GPU-hour on-demand. Compare the exact variants, memory and published specifications below. GPU spec numbers are not benchmarks.
61.1% cheaper at A100.
checked 13 October 2026. Price alone does not establish equivalent capacity or performance.
A100
GH200
Spec sheet
| A100 | GH200 | |
|---|---|---|
| Spec variant | A100 SXM 40GB | GH200 |
| Architecture | Ampere | Hopper |
| VRAM (spec variant) | 40 GB | 96 GB |
| FP16 TFLOPS (dense) | 312 | 989 |
| Memory bandwidth | 1555 GB/s | 4000 GB/s |
| TDP | 400 W | 700 W |
| Interconnect | NVLink 600GB/s | NVLink-C2C 900GB/s |
| Launched | 2020 | 2023 |
Rental price per manufacturer-rated FP16 compute: A100 $2.85 per PFLOP-hour vs GH200 $2.32. Formula: cheapest $/hr ÷ dense FP16 PFLOPS (1 PFLOP = 1000 TFLOPS). This uses A100 SXM 40GB and GH200, whose datasheets may differ from the variants above. It is not measured job throughput. Specs: A100 manufacturer, GH200 manufacturer.
What they cost to rent (13 October 2026)
| A100 | GH200 | |
|---|---|---|
| Cheapest on-demand $/hr | $0.89 | $2.29 |
| Cheapest spot/community $/hr | $0.68 | – |
| Cheapest source | Jarvislabs | Lambda |
| Providers offering it | 22 | 3 |
Cheapest on-demand rate; the cheaper one is highlighted. Spot/marketplace tiers shown on the individual pages.
FAQ
A100 is cheaper: the A100 rents from $0.89 per GPU-hour and the GH200 from $2.29 on-demand, checked 13 October 2026.
The largest recorded A100 variant has 80 GB and the largest GH200 variant has 96 GB. Other variants may have less memory. The GH200 has more.
Compare more rental options: the screener · price movers · methodology.