T2D family · General Purposearm64 · Ampere

t2d-standard-32

The t2d-standard-32 machine type has 32 vCPUs and 128 GB of memory. Pricing for this instance starts at $1.35 per hour and $986.87 monthly in the us-central1 region.

Updated June 17, 2026
vCPUs
32
Memory
128 GB
Network
Up to 32 Gbps
Storage
Persistent Disk

Save up to $710/mo on every t2d-standard-32

Connect Google Cloud — we'll find the optimal pricing model for your workload.

All pricing options

us-central1 · USD · monthly = 730 hrs
Prices exclude local taxes
TermHourlyMonthlySavings
On-Demand
$1.3519$986.87 Baseline
1-Year Committed Use Discount (CUD)
$0.8516$621.70 -37%
3-Year Committed Use Discount (CUD)
$0.6084$444.12 -55%
Preemptible / Spot
$0.3789$276.63 -72%
You could save $710.24/mo on this instance with the right pricing model.
Find my savings

Monthly cost estimator

Estimate your spend based on actual usage.
730 h
1h365h730h (24/7)
1
Estimated monthly
$986.87
730 hrs × $1.3519/hr × 1

Compute

arm64 · Ampere
vCPUs i32
Memory i128 GB
Physical processorAMD Milan
Nested VirtualizationNot supported
Sole TenantNot supported
GPUNone
Within T2D family
t2d-standard-1
1 vCPU
t2d-standard-2
2 vCPU
t2d-standard-4
4 vCPU
t2d-standard-8
8 vCPU
t2d-standard-16
16 vCPU
t2d-standard-32
32 vCPU
t2d-standard-48
48 vCPU
t2d-standard-60
60 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 bandwidth32 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.
Spect2d-standard-32t2d-standard-1Δ
vCPUs321-97%
Memory128 GB4 GB-97%
Hourly Price$1.3519$0.0422-97%
Monthly Price$986.87$30.84-97%
Cost optimization

GCP recommender alerts can cut this bill ~30-40%.

Connect your GCP account. We'll identify every underutilized t2d.* instance and show exactly where downsizing, cleaning up orphaned disks, or shifting to CUDs saves money — with zero code changes.