PlatformHow it worksFinOps LeadershipPricingBlogEventsCalculatorFor FinanceFor EngineeringFor FinOpsAboutCareersContact Book a demo

g7e.12xlarge pricing and specs in Asia Pacific (Mumbai)

48 vCPU · 512 GiB · 400 Gigabit · Intel Xeon Scalable (Emerald Rapids)

$13.5338/hour on-demand · $9,880/month (Linux, Shared)

g7e.12xlarge is a GPU EC2 instance with 48 vCPU and 512 GiB, generation 7 of the g family. On-demand it costs $13.5338 an hour, about $9,880 a month if it runs all month. A one-year commitment with nothing up front works out at $8.5263 an hour and pays for itself above roughly 459 hours a month; below that, on-demand is cheaper. The three-year options go down to $5.8466 an hour, 57% below on-demand. There is no newer generation at this size in Asia Pacific (Mumbai). Across regions the cheapest place to run g7e.12xlarge is US East (N. Virginia) (us-east-1) at $8.2861 an hour, 39% below Asia Pacific (Mumbai).

Pricing by OS (hourly, USD, Shared)

OptionLinuxWindowsRHELSUSE
On-Demand$13.5338$15.7418$14.0522$13.6588
Spot$13.5338$15.7418——
1y Compute SP NU$10.6578$12.8658$11.1762$10.7177
3y Compute SP NU$7.8929$10.1009$8.4113$7.9469
1y EC2 SP NU$8.5263$10.7343$9.0447$8.5862
3y EC2 SP NU$5.8466$8.0546$6.3650$5.9006

Spot by AZ (7-day p50, Linux): ap-south-1b $13.5338 · ap-south-1a $13.5338

Newer generations of the same size

Same family letter and size in a newer generation, ranked by price. “vCPU per $” uses vCPU as the performance proxy — newer chips usually add more, so it is a floor.

No Graviton equivalent at this size

No newer generation of this size is priced in Asia Pacific (Mumbai).

Cheapest regions for g7e.12xlarge

RegionOn-Demand $/hvs ap-south-1Saves / mo
US East (N. Virginia) us-east-1$8.2861-39%$3,831
US East (Ohio) us-east-2$8.2861-39%$3,831
US West (Oregon) us-west-2$8.2861-39%$3,831
Europe (Spain) eu-south-2$8.7313-35%$3,506
Asia Pacific (Seoul) ap-northeast-2$10.1873-25%$2,443
EU (Stockholm) eu-north-1$11.9533-12%$1,154

Caveat: instance price is only part of the bill. Cross-region and internet data transfer, latency to your users, data-residency rules and service availability can outweigh a few percent on compute.

Price history (ap-south-1)

Daily snapshots since the catalog started tracking this type; a row is added whenever a headline price changes.

DateOD LinuxOD Windows1y RI3y RISpot p50
2026-09-24$13.5338$15.7418——$13.5338
2026-09-23$13.5338$15.7418——$13.4492
2026-09-22$13.5338$15.7418——$13.0689

All attributes

vCPU
48
Cores / threads per core
24 / 2
Memory
512 GiB
Memory per vCPU
10.67 GiB
Processor
Intel Xeon Scalable (Emerald Rapids)
Architecture
x86_64
Sustained clock
2.4 GHz
Hypervisor
nitro
Generation
Current
Burstable
No
Bare metal
No
Free tier eligible
No
Network performance
400 Gigabit
Network baseline / burst
400.0 / 400.0 Gbps
Max ENIs × IPv4 per ENI
10 × 64
IPv6 / ENA / EFA
IPv6 / ENA / EFA
EBS optimized
Yes
EBS bandwidth (baseline / max)
25000 / 25000 Mbps
EBS IOPS (baseline / max)
100,000 / 100000
EBS NVMe
required
Instance storage
3800 GB NVMe SSD
GPU
2 × NVIDIA RTX PRO Server 6000 (192.0 GiB total)
Placement groups
cluster, partition, spread
Hibernation / Nitro Enclaves
No / Yes
Dedicated hosts
Supported
Boot modes
legacy-bios, uefi
Spot supported
Yes

Embed this price card

A tiny live widget for your docs or blog, with a “Powered by TruCost” link.

<iframe src="https://trucost.cloud/instances/embed?service=ec2&region=ap-south-1&type=g7e.12xlarge" width="420" height="260" style="border:1px solid #e2e8f0;border-radius:12px" loading="lazy" title="g7e.12xlarge pricing by TruCost"></iframe>

Public AWS list prices (USD), refreshed nightly (catalog 2026-10-10). RI and Savings Plan rates are effective hourly (upfront amortised over the term) and are charged for every hour of the term. Excludes taxes, data transfer and storage. How these numbers are sourced and checked. Not affiliated with Amazon Web Services.

List prices are where it starts. Your bill is where it matters.

TruCost reads your actual AWS usage and tells you which of these commitments you should really buy, what your idle capacity costs, and where every dollar of the bill goes. Thirty minutes on your own data.

See it on your AWS bill
Book a demo