Previous generation M1 family · Memory Optimizedx86_64 · Intel/AMD

m1-megamem-96

The m1-megamem-96 machine type has 96 vCPUs and 1433.6 GB of memory. Pricing for this instance starts at $10.65 per hour and $7776.08 monthly in the us-central1 region.

Updated June 26, 2026
vCPUs
96
Memory
1433.6 GB
Network
Up to 32 Gbps
Storage
Local SSD

Save up to $6189/mo on every m1-megamem-96

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
$10.6522$7776.08 Baseline
1-Year Committed Use Discount (CUD)
$6.3023$4600.66 -41%
3-Year Committed Use Discount (CUD)
$3.1966$2333.52 -70%
Preemptible / Spot
$2.1740$1587.00 -80%
You could save $6189.07/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
$7776.08
730 hrs × $10.6522/hr × 1

Compute

x86_64 · Intel/AMD
vCPUs i96
Memory i1433.6 GB
Physical processorIntel Skylake
Nested VirtualizationNot supported
Sole TenantNot supported
GPUNone
Within M1 family
m1-ultramem-40
40 vCPU
m1-megamem-96
96 vCPU
m1-ultramem-80
80 vCPU
m1-ultramem-160
160 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 SSDsSupported (Scratch Disk)

Compare with another instance

vs.
Specm1-megamem-96m1-ultramem-40Δ
vCPUs9640-58%
Memory1433.6 GB961 GB-33%
Hourly Price$10.6522$6.2931-41%
Monthly Price$7776.08$4593.96-41%
Cost optimization

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

Connect your GCP account. We'll identify every underutilized m1.* instance and show exactly where downsizing, cleaning up orphaned disks, or shifting to CUDs saves money — with zero code changes.