x2gd.12xlarge pricing and specs in EU (Ireland)
48 vCPU · 768 GiB · 20 Gigabit · AWS Graviton2 Processor Graviton
$4.8000/hour on-demand · $3,504/month (Linux, Shared)
x2gd.12xlarge is a high-memory EC2 instance with 48 vCPU and 768 GiB, generation 2 of the x family on AWS Graviton (Arm). On-demand it costs $4.8000 an hour, about $3,504 a month if it runs all month. A one-year commitment with nothing up front works out at $2.9575 an hour and pays for itself above roughly 449 hours a month; below that, on-demand is cheaper. The three-year options go down to $1.4267 an hour, 70% below on-demand. The newer x8g.12xlarge offers the same size for $5.6160 an hour, 17% more. Across regions the cheapest place to run x2gd.12xlarge is US East (N. Virginia) (us-east-1) at $4.0080 an hour, 16% below EU (Ireland).
Pricing by OS (hourly, USD, Shared)
| Option | Linux | Windows | RHEL | SUSE | Ubuntu Pro |
|---|---|---|---|---|---|
| On-Demand | $4.8000 | — | $5.3184 | $4.9250 | $4.8840 |
| Spot | $1.8857 | — | — | — | — |
| 1y Std RI NU | $2.9575 | — | $3.4759 | $3.0175 | — |
| 1y Std RI PU | $2.8166 | — | $3.3350 | $2.8765 | — |
| 1y Std RI AU | $2.7603 | — | $3.2787 | $2.8202 | — |
| 3y Std RI NU | $1.6392 | — | $2.1576 | $1.6932 | — |
| 3y Std RI PU | $1.5178 | — | $2.0362 | $1.5718 | — |
| 3y Std RI AU | $1.4267 | — | $1.9451 | $1.4807 | — |
| 1y Conv RI NU | $3.5492 | — | $4.0676 | $3.6092 | — |
| 3y Conv RI NU | $1.9673 | — | $2.4857 | $2.0213 | — |
| 1y Compute SP NU | $3.5492 | — | $4.0676 | $3.6091 | $3.6164 |
| 3y Compute SP NU | $1.9673 | — | $2.4857 | $2.0213 | $2.0220 |
| 1y EC2 SP NU | $2.9575 | — | $3.4759 | $3.0174 | $3.0247 |
| 3y EC2 SP NU | $1.6392 | — | $2.1576 | $1.6932 | $1.6939 |
Spot by AZ (7-day p50, Linux): eu-west-1b $1.7044 · eu-west-1a $1.8857 · eu-west-1c $1.9501
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.
Already Graviton| Type | $/h | Price Δ | vCPU per $ Δ | Saves / mo |
|---|---|---|---|---|
| x8g.12xlarge Graviton | $5.6160 | +17% | -15% | $-596 |
| x8i.12xlarge arch change | $6.3024 | +31% | -24% | $-1,097 |
| x2iezn.12xlarge arch change | $12.0000 | +150% | -60% | $-5,256 |
| x8aedz.12xlarge arch change | $16.5686 | +245% | -71% | $-8,591 |
Cheapest regions for x2gd.12xlarge
| Region | On-Demand $/h | vs eu-west-1 | Saves / mo |
|---|---|---|---|
| US East (N. Virginia) us-east-1 | $4.0080 | -16% | $578 |
| US East (Ohio) us-east-2 | $4.0080 | -16% | $578 |
| US West (Oregon) us-west-2 | $4.0080 | -16% | $578 |
| EU (Ireland) eu-west-1 | $4.8000 | current | — |
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 (eu-west-1)
Daily snapshots since the catalog started tracking this type; a row is added whenever a headline price changes.
| Date | OD Linux | OD Windows | 1y RI | 3y RI | Spot p50 |
|---|---|---|---|---|---|
| 2026-10-22 | $4.8000 | — | $2.9575 | $1.6392 | $1.8857 |
| 2026-10-21 | $4.8000 | — | $2.9575 | $1.6392 | $1.8896 |
| 2026-10-20 | $4.8000 | — | $2.9575 | $1.6392 | $1.8947 |
| 2026-10-19 | $4.8000 | — | $2.9575 | $1.6392 | $1.8685 |
| 2026-10-16 | $4.8000 | — | $2.9575 | $1.6392 | $1.8696 |
| 2026-10-15 | $4.8000 | — | $2.9575 | $1.6392 | $1.8478 |
| 2026-10-14 | $4.8000 | — | $2.9575 | $1.6392 | $1.7528 |
| 2026-10-13 | $4.8000 | — | $2.9575 | $1.6392 | $1.6580 |
| 2026-10-12 | $4.8000 | — | $2.9575 | $1.6392 | $1.6176 |
| 2026-10-11 | $4.8000 | — | $2.9575 | $1.6392 | $1.5283 |
| 2026-10-10 | $4.8000 | — | $2.9575 | $1.6392 | $1.4825 |
| 2026-10-09 | $4.8000 | — | $2.9575 | $1.6392 | $1.4790 |
| 2026-10-08 | $4.8000 | — | $2.9575 | $1.6392 | $1.4577 |
| 2026-10-07 | $4.8000 | — | $2.9575 | $1.6392 | $1.4474 |
| 2026-10-06 | $4.8000 | — | $2.9575 | $1.6392 | $1.4131 |
| 2026-10-05 | $4.8000 | — | $2.9575 | $1.6392 | $1.4018 |
| 2026-10-04 | $4.8000 | — | $2.9575 | $1.6392 | $1.3530 |
| 2026-10-03 | $4.8000 | — | $2.9575 | $1.6392 | $1.3286 |
| 2026-10-02 | $4.8000 | — | $2.9575 | $1.6392 | $1.3265 |
| 2026-09-30 | $4.8000 | — | $2.9575 | $1.6392 | $1.3244 |
| 2026-09-29 | $4.8000 | — | $2.9575 | $1.6392 | $1.3265 |
| 2026-09-28 | $4.8000 | — | $2.9575 | $1.6392 | $1.3298 |
| 2026-09-27 | $4.8000 | — | $2.9575 | $1.6392 | $1.3312 |
| 2026-09-26 | $4.8000 | — | $2.9575 | $1.6392 | $1.3382 |
| 2026-09-25 | $4.8000 | — | $2.9575 | $1.6392 | $1.3499 |
| 2026-09-24 | $4.8000 | — | $2.9575 | $1.6392 | $1.3514 |
| 2026-09-23 | $4.8000 | — | $2.9575 | $1.6392 | $1.3536 |
| 2026-09-22 | $4.8000 | — | $2.9575 | $1.6392 | $1.3549 |
All attributes
- vCPU
- 48
- Cores / threads per core
- 48 / 1
- Memory
- 768 GiB
- Memory per vCPU
- 16.00 GiB
- Processor
- AWS Graviton2 Processor
- Architecture
- arm64
- Sustained clock
- 2.5 GHz
- Hypervisor
- nitro
- Generation
- Current
- Burstable
- No
- Bare metal
- No
- Free tier eligible
- No
- Network performance
- 20 Gigabit
- Network baseline / burst
- 20.0 / 20.0 Gbps
- Max ENIs × IPv4 per ENI
- 8 × 30
- IPv6 / ENA / EFA
- IPv6 / ENA / —
- EBS optimized
- Yes
- EBS bandwidth (baseline / max)
- 14250 / 14250 Mbps
- EBS IOPS (baseline / max)
- 60,000 / 60000
- EBS NVMe
- required
- Instance storage
- 2 × 1425 GB NVMe SSD
- GPU
- —
- Placement groups
- cluster, partition, spread
- Hibernation / Nitro Enclaves
- No / Yes
- Dedicated hosts
- Supported
- Boot modes
- uefi
- Spot supported
- Yes
Public AWS list prices (USD), refreshed nightly (catalog 2026-10-22). 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.