GCP Compute Instance

a3-highgpu-2g

The a3-highgpu-2g is a GPU-accelerated GCP Compute instance with 52 vCPUs and 468 GB of memory, 2 H100 GPUs, powered by Intel. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $21.9581/hr in us-central1.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-central1$21.958$9.416$15.948
us-east4$21.958$6.700$15.276
us-west1$21.958$9.416$15.948
asia-south1$22.836$6.985$15.852
europe-north1$24.178$2.344$16.783
europe-west1$24.178$7.057$16.783
us-east5$24.731$6.889$17.110
us-west4$24.731$7.217$17.205
asia-east1$25.425$8.515$17.649
europe-west8$25.471$2.534$17.681
europe-west9$25.471$5.917$17.681
europe-west3$25.911$7.564$18.036
asia-south2$26.374$6.649$18.308
australia-southeast1$27.448$7.709$19.148
europe-west4$27.954$8.157$19.914
asia-southeast1$28.389$9.073$19.706
asia-northeast1$31.447$7.799$21.884

Frequently Asked Questions

What is the a3-highgpu-2g?
The a3-highgpu-2g is a GPU-accelerated GCP Compute instance with 52 vCPUs and 468 GB of memory, 2 H100 GPUs, powered by Intel. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $21.9581/hr in us-central1.
What is the cheapest region for a3-highgpu-2g?
us-central1 at $21.958/hr on-demand.
How much does a3-highgpu-2g cost per month?
Starting at $16029.43/mo on-demand in us-central1, or $1711.25/mo with spot pricing.

Run a free assessment to identify overprovisioned workloads, idle capacity, and your potential savings, in minutes.

Most clusters are overprovisioned.
Let's prove yours is.