Comparison · GPU vs GPU · read 00:32 UTCH200 NVL vs H100 NVL
Specifications, today's prices from 27 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.
| H200 NVL | H100 NVL | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 141 GB | 94 GB | +50% |
| Memory bandwidth | 4.80 TB/s | 3.94 TB/s | +22% |
| FP16 tensor | — | — | — |
| FP32 | — | — | — |
| Power | — | — | — |
| Prices today | |||
| Cheapest on-demand | $2.67 | $1.88 | +42% |
| Median on-demand | $4.14 | $3.94 | +5% |
| Highest on-demand | $8.88 | $8.98 | -1% |
| Cheapest spot | $1.33 | $0.63 | +113% |
| Cheapest reserved | $2.38 | $1.99 | +20% |
| Current offers (n) | 27 | 36 | -25% |
| Providers with a fresh offer | 12 | 15 | -20% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.019 | $0.020 | -5% |
| Per GB of VRAM · hour (median) | $0.029 | $0.042 | -30% |
| Per PFLOP FP16 · hour (median) | — | — | — |
| Per TB/s · hour (median) | $0.861 | $1.001 | -14% |
| Trend | |||
| 30-day median change | +27.2% | +18.2% | — |
| 90-day median change | +7.8% | +16.9% | — |
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
Vast.aiTrust 784× $2.67 - 2
Airon AI1× $2.70 - 3
IONOS2× $3.26
- 1Airon AI1× $1.88
- 2
GPU.ai8× $2.06 - 3Vast.aiTrust 781× $2.34
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the H200 NVL if…
- your model needs more than 94 GB per GPU: 141 GB against 94 GB.
- you serve LLMs: memory bandwidth per dollar is better ($0.861 per TB/s-hour against $1.001).
Choose the H100 NVL if…
- the hourly price matters most: median $3.94 against $4.14, 5% less.
- you want choice: 15 providers have a fresh offer today against 12.
Questions about H200 NVL vs H100 NVL
Which is cheaper to rent, the H200 NVL or the H100 NVL?
Today the cheapest current on-demand H200 NVL is $2.67 per GPU-hour and the cheapest H100 NVL is $1.88; medians are $4.14 and $3.94. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the H200 NVL and H100 NVL have?
141 GB of HBM3 on the H200 NVL, 94 GB of HBM3 on the H100 NVL, at 4.80 and 3.94 TB/s.
Where do these numbers come from?
From 63 current offers read on the providers' own pages and APIs over the last 45 days (reference 00:32 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.