All pricing options
us-central1 · USD · monthly = 730 hrs
Prices exclude local taxes
| Term | Hourly | Monthly | Savings |
|---|---|---|---|
On-Demand | $3.4301 | $2503.96 | Baseline |
1-Year Committed Use Discount (CUD) | $2.1609 | $1577.43 | -37% |
3-Year Committed Use Discount (CUD) | $1.5437 | $1126.89 | -55% |
Preemptible / Spot | $1.5130 | $1104.46 | -56% |
You could save $1399.50/mo on this instance with the right pricing model.
Find my savings Monthly cost estimator
Estimate your spend based on actual usage.
730 h
1
Estimated monthly
$2503.96
730 hrs × $3.4301/hr × 1
Compute
vCPUs i96
Memory i192 GB
Physical processorAMD Turin
Nested VirtualizationNot supported
Sole TenantNot supported
GPUNone
Within N4D family
n4d-highcpu-22 vCPU
n4d-standard-22 vCPU
n4d-highmem-22 vCPU
n4d-highcpu-44 vCPU
n4d-standard-44 vCPU
n4d-highmem-44 vCPU
n4d-highcpu-88 vCPU
n4d-standard-88 vCPU
n4d-highmem-88 vCPU
n4d-highcpu-1616 vCPU
n4d-standard-1616 vCPU
n4d-highmem-1616 vCPU
n4d-highcpu-3232 vCPU
n4d-standard-3232 vCPU
n4d-highcpu-4848 vCPU
n4d-highmem-3232 vCPU
n4d-standard-4848 vCPU
n4d-highcpu-6464 vCPU
n4d-highmem-4848 vCPU
n4d-standard-6464 vCPU
n4d-highcpu-8080 vCPU
n4d-standard-8080 vCPU
n4d-highcpu-9696 vCPU
n4d-highmem-6464 vCPU
n4d-standard-9696 vCPU
n4d-highmem-8080 vCPU
n4d-highmem-9696 vCPU
Lock in this rate across your fleet — typically save 30–40%
Connect your Google Cloud account to apply this pricing logic to every running instance automatically.
Networking
Max egress bandwidth50 Gbps
Tier 1 bandwidthN/A
Enhanced networking iYes (gvnic/virtio)
IPv6 supportYes (Dual-stack VPC)
Storage
Max persistent disks128
Max disk size512 TB
Local SSDsNo local SSD
Compare with another instance
vs.
Specn4d-highcpu-96n4d-highcpu-2Δ
vCPUs962-98%
Memory192 GB4 GB-98%
Hourly Price$3.4301$0.0715-98%
Monthly Price$2503.96$52.17-98%
Cost optimization
GCP recommender alerts can cut this bill ~30-40%.
Connect your GCP account. We'll identify every underutilized n4d.* instance and show exactly where downsizing, cleaning up orphaned disks, or shifting to CUDs saves money — with zero code changes.