GPU comparison
A100 vs H100: specs and rental prices
NVIDIA A100 against NVIDIA H100: 80 GB against 80 GB of memory, lowest listed on-demand price $1.35 against $2.50 per GPU-hour. Specs from NVIDIA, prices as of Oct 25, 2026.
In short
- Both list 80 GB of GPU memory.
- Memory type is HBM2e on the A100 and HBM3 on the H100.
- The H100 lists 3,350 GB/s of memory bandwidth against 2,039 GB/s for the A100: 1.64× higher.
- The H100 lists 1,979 TFLOPS of FP16 / BF16 tensor throughput against 624 TFLOPS for the A100: 3.17× higher.
- Maximum power is listed at 400 W for the A100 and 700 W for the H100.
- Not every figure can be compared: at least one vendor page does not publish: FP8 tensor throughput.
- The lowest listed on-demand price is $1.35 per GPU-hour for the A100 (Hyperstack) and $2.50 for the H100 (Hyperstack).
- Per GB of GPU memory that is $0.017 per hour for the A100 and $0.031 for the H100.
This summary is generated from the tables below. Prices were last checked Oct 25, 2026. A listing not re-checked for 7 days is greyed and left out of every lowest-price figure; after 14 days it is removed from the page.
Specifications side by side
| Specification | A100 80GB SXM | H100 SXM | Difference |
|---|---|---|---|
| GPU memory | 80 GB | 80 GB | Same |
| Memory type | HBM2e | HBM3 | Different |
| Memory bandwidth | 2,039 GB/s | 3,350 GB/s | H100 1.64× higher |
| FP8 tensor throughput | Not published | 3,958 TFLOPS (with sparsity) | — |
| FP16 / BF16 tensor throughput, with sparsity | 624 TFLOPS | 1,979 TFLOPS | H100 3.17× higher |
| TF32 tensor throughput, with sparsity | 312 TFLOPS | 989 TFLOPS | H100 3.17× higher |
| FP64 throughput | 9.7 TFLOPS | 34 TFLOPS | H100 3.51× higher |
| Maximum power | 400 W | 700 W | H100 1.75× higher |
| GPU-to-GPU interconnect | 600 GB/s | 900 GB/s | H100 1.5× higher |
Compared versions: A100 80GB SXM and H100 SXM. The figure in the stronger cell is shaded; power is shown without a winner. Two throughput figures are compared only when both vendors state them on the same basis (both with sparsity, or both dense), and “derived” means a total the vendor publishes divided by the GPU count it publishes. Full tables with sources: A100 specifications · H100 specifications.
Rental prices
| Rental price | A100 | H100 | Difference |
|---|---|---|---|
| Lowest listed on-demand price | $1.35 per GPU-hour · Hyperstack · checked Oct 25, 2026 | $2.50 per GPU-hour · Hyperstack · checked Oct 25, 2026 | H100 1.85× higher |
| Lowest listed spot price | $1.06 per GPU-hour · Microsoft Azure · checked Oct 25, 2026 | $0.79 per GPU-hour · Nebius · checked Oct 25, 2026 | A100 1.34× higher |
| Price per GB of memory | $0.017 per GB of GPU memory per hour | $0.031 per GB of GPU memory per hour | H100 1.85× higher |
| Fresh listings | 14 from 9 providers | 26 from 12 providers | — |
Prices cover every version and instance size the providers list, so they are not tied to the versions compared above; the price per GB of memory divides the lowest fresh on-demand price by the memory of the compared version. Listed prices are not like for like across providers. See every listing: A100 prices · H100 prices.
More on these GPUs
Cite this page
Last updated Oct 25, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). A100 vs H100. Retrieved from https://datacentercensus.com/gpu-prices/compare/a100-vs-h100 |
|---|---|
| MLA | “A100 vs H100.” Data Center Census, Oct 25, 2026, https://datacentercensus.com/gpu-prices/compare/a100-vs-h100. |
| Link | https://datacentercensus.com/gpu-prices/compare/a100-vs-h100 |
Republishing a figure or table? Attribute it to Data Center Census with a link to this page. The underlying data is downloadable as JSON and CSV; the press kit has standing figures and contact details.