3/7
Providers w/ Spot
$0.28
Lowest Spot /hr
72%
Max Savings vs On-Demand
Hardware Specifications
Ampere
24 GB GDDR6
VRAM
125 TFLOPS
FP16 Performance
31.2 TFLOPS
FP32 Performance
150W
Thermal Design Power
600 GB/s
Memory Bandwidth
Ampere
GPU Architecture
Provider Spot Price On-Demand Savings Availability
Amazon Web Services $0.58/hr $1.01/hr 42% Available
GCP
Azure
Lambda Cloud $0.60/hr $0.60/hr -1% Available
CoreWeave
RunPod $0.28/hr $0.37/hr 24% Available
Vast.ai
What is GPU Spot Pricing?

GPU spot instances use unused cloud capacity at discounts of 60–90% compared to on-demand pricing. The tradeoff: cloud providers can reclaim instances with little notice (typically 30 seconds warning). For fault-tolerant workloads like batch inference, training, and CI/CD, spot pricing dramatically reduces GPU costs.

RoofRun monitors prices from 7 providers every 30 minutes and surfaces the cheapest A10G prices so you don't have to check each provider manually.