Pick up to four instance types from one cloud and compare their specs, pricing, and cost efficiency in a single region. Looking for instances by vCPU or memory range instead? Browse by spec.
| GPU-accelerateda2-highgpu-1g | GPU-accelerateda2-highgpu-4g | |
|---|---|---|
| Compute | ||
| vCPUs | 12 | 48 |
| Memory | 85 GB | 340 GB |
| Memory per vCPU | 7.08 GB | 7.08 GB |
| Architecture | x64 | x64 |
| Processor | Intel | Intel |
| Family | a2-highgpu | a2-highgpu |
| Category | GPU-accelerated | GPU-accelerated |
| GPU | ||
| GPUs | 1× A100 | 4× A100 |
| GPU memory | 40 GB | 160 GB |
| $ / GPU / hr | $3.673 | $3.673 |
| Price in us-central1 | ||
| On-demand | $3.673$2681.57/mo | $14.694$10726.28/mo |
| Spot | $2.121$1548.19/mo | $8.483$6192.77/mo |
| Reserved 1-year | $2.31437% off on-demand | $9.25737% off on-demand |
| Reserved 3-year | $1.28665% off on-demand | $5.14365% off on-demand |
| Spot savings | 42% | 42% |
| Cost efficiency in us-central1 | ||
| $ / vCPU / hr | $0.3061 | $0.3061 |
| $ / GB RAM / hr | $0.0432 | $0.0432 |
| Availability | ||
| Regions | 10 | 10 |
| Cheapest region | us-central1 · $3.673 | us-central1 · $14.694 |
| Cheapest spot region | us-west4 · $2.098 | us-west4 · $8.392 |
| Price snapshot | 2026-09-05 | 2026-09-05 |