NVIDIA · Pascal · 16 GB HBM2 · PCIe · 2016
2 providers · 2 configurations · prices as of Sep 27, 2026, 01:12 UTC
Daily P100 prices per GPU-hour. The shaded period is reconstructed from the version history of SkyPilot's public price catalogs (fewer providers than live data); after that, PetaPrice's own tracking.
Cheapest On-demand P100 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($1.28).
2 providers · 2 configurations
GPUs with similar compute and memory, and their lowest on-demand price right now.
On-demand P100 prices start at $1.28 per GPU-hour (Oracle Cloud). The median across 2 providers is $1.33, and the most expensive is $1.39. Running one GPU around the clock costs about $931 per month at the lowest price.
At $1.28 per hour and 0.0187 PF of dense FP16/BF16, the P100 costs $68.2 per PFLOP-hour. That ranks 70 of 70 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
16 GB HBM2 with 732 GB/s of memory bandwidth, Pascal architecture (2016), PCIe form factor, 250 W. Dense peak: 0.0187 PF FP16 / BF16, 0.0093 PF FP32, 0.0047 PF FP64.
Prices were collected on Sep 27, 2026, 01:12 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.