2/7
Providers w/ Spot
$0.13
Lowest Spot /hr
81%
Max Savings vs On-Demand
Hardware Specifications
Ada Lovelace
24 GB GDDR6X
VRAM
165 TFLOPS
FP16 Performance
82.6 TFLOPS
FP32 Performance
450W
Thermal Design Power
1.0 TB/s
Memory Bandwidth
Ada Lovelace
GPU Architecture
Provider Spot Price On-Demand Savings Availability
AWS
GCP
Azure
Lambda
CoreWeave
RunPod $0.34/hr $0.69/hr 51% Available
Vast.ai $0.13/hr $0.19/hr 29% Available
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 RTX 4090 prices so you don't have to check each provider manually.