How much does an idle g6e.16xlarge cost on AWS?
A g6e.16xlarge billed on-demand and left running around the clock costs about $5,531/mo at its cheapest listed region (us-east-1). Scheduling it off outside business hours cuts that to roughly $1,646/mo — a $3,885/mo saving.
Cheapest on-demand
$7.5772/hr
us-east-1
Running 24/7
$5,531/mo
730-hour month
Business-hours savings
$3,885/mo
up to 70% off the 24/7 bill (est.)
Price by region
| Region | Hourly (on-demand) | Spot (typical) | ≈ Monthly (24/7) |
|---|---|---|---|
| us-east-1 Cheapest | $7.5772/hr | $2.5005/hr | ≈ $5,531/mo |
| us-east-2 | $7.5772/hr | $1.5912/hr | ≈ $5,531/mo |
| us-west-2 | $7.5772/hr | $2.5762/hr | ≈ $5,531/mo |
| ap-south-1 | $9.1000/hr | — | ≈ $6,643/mo |
| eu-central-1 | $9.4745/hr | $2.1791/hr | ≈ $6,916/mo |
| ap-northeast-1 | $10.9892/hr | $3.2968/hr | ≈ $8,022/mo |
What a schedule saves
| Schedule | Monthly cost | Savings vs 24/7 |
|---|---|---|
| Running 24/7 | $5,531/mo | baseline |
| Weekdays only (off on weekends) | $3,951/mo | -$1,580/mo (29%) |
| Business hours only (10×5) | $1,646/mo | -$3,885/mo (70%) |
Assumes a 730-hour month at on-demand list price. Actual savings depend on when the instance is actually used.
About the g6e family
G6e pairs the NVIDIA L40S — 48 GB of VRAM per GPU — with the G6 platform, filling the gap between the inference-tier L4 and the training-tier flagships. It fits fine-tuning, heavier inference, and rendering work that outgrows an L4 but doesn't justify a multi-GPU training rig. Those are bursty, working-session workloads by nature, and a g6e left running between sessions bills for premium silicon that is producing nothing.
Regional pricing varies: g6e.16xlarge runs $7.5772/hr in us-east-1, the cheapest region priced here, versus $10.9892/hr in ap-northeast-1, the priciest — a 31% spread across regions for the identical instance type.
Common questions
How much does an idle g6e.16xlarge cost per month?
At the cheapest listed region (us-east-1), a g6e.16xlarge costs $7.5772/hr, or about $5,531/mo if it runs 24/7. That's the on-demand list price — an idle instance costs exactly the same as a busy one, since cloud billing doesn't know the difference.
How much can I save by scheduling it off outside work hours?
Restricting it to business hours only (10×5) saves about $3,885/mo (70%) versus running 24/7. A lighter schedule — on around the clock on weekdays, off on weekends — still saves about $1,580/mo (29%).
Where does g6e fit between g6 and the p-series?
The L40S is the "one big GPU" tier, and 48 GB is the number that matters: it is enough to serve a 30B-class model in fp16 on one card, QLoRA-tune something larger, run bigger batch sizes, or hold longer contexts than fit on a 24 GB L4. If none of those apply to your workload, the extra VRAM is just idle capacity. If a g6e mostly runs during working sessions, scheduling it off between sessions usually matters more than which GPU tier was picked.
Other g6e sizes
Stop paying for idle AWS servers
Idlefy runs a free audit of your fleet, then flips dev servers to stopped-by-default: lease one when you need it, and
when the lease ends it shuts itself off — stop, not terminate, persistent disks intact. Timers are set by your team, never
guessed, and Idlefy only manages instances tagged idlefy=enabled — on AWS that boundary is enforced by the IAM policy itself.
Prices are on-demand list price for Linux instances and exclude storage, network, data transfer, and any negotiated or volume discounts. Actual bills vary by usage and account-level pricing. Prices as of 2026-08-31. Spot figures are indicative — AWS values are derived from AWS's published typical savings vs on-demand for the region; GCP values are the listed Spot price. Spot capacity can be reclaimed by the provider. Stopping preserves EBS and persistent-disk volumes; data on local instance-store or local-SSD drives does not survive a stop.