NVIDIA · Ampere · 24 GB GDDR6 · PCIe · 2021
1 providers · 6 configurations · prices as of Sep 27, 2026, 01:12 UTC
Daily A10G 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 A10G offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($1.01).
1 providers · 6 configurations
GPUs with similar compute and memory, and their lowest on-demand price right now.
On-demand A10G prices start at $1.01 per GPU-hour (AWS). The median across 1 providers is $1.01, and the most expensive is $1.01. Running one GPU around the clock costs about $734 per month at the lowest price.
Yes. Spot (interruptible) A10G capacity starts at $0.13 per GPU-hour, 87% below the cheapest on-demand price. Spot instances can be preempted at any time, so use them for checkpointed training or batch jobs.
At $1.01 per hour and 0.07 PF of dense FP16/BF16, the A10G costs $14.4 per PFLOP-hour. That ranks 68 of 70 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
24 GB GDDR6 with 600 GB/s of memory bandwidth, Ampere architecture (2021), PCIe form factor, 150 W. Dense peak: 0.07 PF FP16 / BF16, 0.14 PF INT8, 0.035 PF TF32, 0.0312 PF FP32, 0.0005 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.