All pricing options
us-central1 · USD · monthly = 730 hrs
Prices exclude local taxes
| Term | Hourly | Monthly | Savings |
|---|---|---|---|
On-Demand | $5.3366 | $3895.75 | Baseline |
1-Year Committed Use Discount (CUD) | $3.3618 | $2454.13 | -37% |
3-Year Committed Use Discount (CUD) | $2.4019 | $1753.40 | -55% |
Preemptible / Spot | $2.3539 | $1718.36 | -56% |
You could save $2177.39/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
$3895.75
730 hrs × $5.3366/hr × 1
Compute
vCPUs i96
Memory i768 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-highmem-96n4d-highcpu-2Δ
vCPUs962-98%
Memory768 GB4 GB-99%
Hourly Price$5.3366$0.0715-99%
Monthly Price$3895.75$52.17-99%
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.