Comparison · GPU vs GPU · read 21:35 UTCH100 vs A100 80GB
Specifications, today's prices from 143 providers, price per unit of memory and compute, and who rents each cheapest. Better values are highlighted; lower is better for prices.
Side by sideSpecs, prices, value
Highlighted cells are the better of the two: more memory and compute, lower prices, lower cost per unit.
| H100 | A100 80GB | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 80 GB | 80 GB | 0% |
| Memory bandwidth | 3.35 TB/s | 2.00 TB/s | +68% |
| FP16 tensor | 989 TFLOPS | 312 TFLOPS | +217% |
| FP32 | 67 TFLOPS | 19.5 TFLOPS | +244% |
| Power | 700 W | 400 W | +75% |
| Prices today | |||
| Cheapest on-demand | $1.35 | $0.60 | +125% |
| Median on-demand | $3.17 | $1.99 | +59% |
| Highest on-demand | $8.98 | $5.29 | +70% |
| Cheapest spot | $0.67 | $0.57 | +17% |
| Cheapest reserved | $1.08 | $0.76 | +42% |
| Current offers (n) | 189 | 181 | +4% |
| Providers with a fresh offer | 76 | 67 | +13% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.017 | $0.008 | +125% |
| Per GB of VRAM · hour (median) | $0.040 | $0.025 | +59% |
| Per PFLOP FP16 · hour (median) | $3.201 | $6.378 | -50% |
| Per TB/s · hour (median) | $0.945 | $0.995 | -5% |
| Trend | |||
| 30-day median change | +3.7% | -3.5% | — |
| 90-day median change | +9.2% | -0.7% | — |
90 days · median on-demand price · rebased to 100How the two have moved
Both medians indexed to 100 ninety days ago, so the slopes compare even though the price levels differ.
Cheapest providers today · on-demand · current offersWho rents each one cheapest
- 1
GPUBankTrust 931× $1.35 - 2
GcoreTrust 801× $1.71 - 3
LiumTrust 408× $1.79
- 1
Vast.aiTrust 784× $0.60 - 2
packet.ai1× $0.89 - 3GPUBankTrust 931× $0.95
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the H100 if…
- you serve LLMs: memory bandwidth per dollar is better ($0.945 per TB/s-hour against $0.995).
- you want choice: 76 providers have a fresh offer today against 67.
Choose the A100 80GB if…
- the hourly price matters most: median $1.99 against $3.17, 37% less.
Questions about H100 vs A100 80GB
Which is cheaper to rent, the H100 or the A100 80GB?
Today the cheapest current on-demand H100 is $1.35 per GPU-hour and the cheapest A100 80GB is $0.60; medians are $3.17 and $1.99. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the H100 and A100 80GB have?
80 GB of HBM3 on the H100, 80 GB of HBM2e on the A100 80GB, at 3.35 and 2.00 TB/s.
Where do these numbers come from?
From 370 current offers read on the providers' own pages and APIs over the last 45 days (reference 21:35 UTC), or in our October 2026 market study for the few providers our collector does not read. Specifications come from manufacturer datasheets. Every price on the GPU pages links to its receipt and shows its read date.