Comparison · GPU vs GPU · read 00:32 UTCT4 vs Tesla P100
Specifications, today's prices from 29 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.
| T4 | Tesla P100 | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 16 GB | 16 GB | 0% |
| Memory bandwidth | 0.30 TB/s | 0.73 TB/s | -59% |
| FP16 tensor | 65 TFLOPS | 18.7 TFLOPS | +248% |
| FP32 | 8.1 TFLOPS | 9.3 TFLOPS | -13% |
| Power | 70 W | 250 W | -72% |
| Prices today | |||
| Cheapest on-demand | $0.20 | $0.04 | +335% |
| Median on-demand | $0.49 | $0.07 | +558% |
| Highest on-demand | $1.22 | $0.11 | +1021% |
| Cheapest spot | $0.07 | $0.04 | +83% |
| Cheapest reserved | $0.17 | $0.22 | -20% |
| Current offers (n) | 87 | 4 | +2075% |
| Providers with a fresh offer | 26 | 3 | +767% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.012 | $0.003 | +335% |
| Per GB of VRAM · hour (median) | $0.031 | $0.005 | +558% |
| Per PFLOP FP16 · hour (median) | $7.580 | $4.005 | +89% |
| Per TB/s · hour (median) | $1.642 | $0.102 | +1505% |
| Trend | |||
| 30-day median change | -13.3% | — | — |
| 90-day median change | -13.3% | — | — |
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
iwinv1× $0.20 - 2
Theta EdgeCloud1× $0.20 - 3
LiumTrust 401× $0.22
- 1
Vast.aiTrust 781× $0.04 - 2
gcube1× $0.07
- 3
Edgevana4× $0.11
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the T4 if…
- you want choice: 26 providers have a fresh offer today against 3.
Choose the Tesla P100 if…
- the hourly price matters most: median $0.07 against $0.49, 85% less.
- you serve LLMs: memory bandwidth per dollar is better ($0.102 per TB/s-hour against $1.642).
Questions about T4 vs Tesla P100
Which is cheaper to rent, the T4 or the Tesla P100?
Today the cheapest current on-demand T4 is $0.20 per GPU-hour and the cheapest Tesla P100 is $0.04; medians are $0.49 and $0.07. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the T4 and Tesla P100 have?
16 GB of memory on the T4, 16 GB of memory on the Tesla P100, at 0.30 and 0.73 TB/s.
Where do these numbers come from?
From 91 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.