g5.4xlarge pricing on AWS, and what idle time costs
g5.4xlarge is an AWS instance with 16 vCPUs, 64 GB of memory and 1× NVIDIA A10G. It costs from $1.624/hr on-demand in us-east-1, about $1,186/mo running 24/7, and indicative spot pricing starts near $0.5359/hr in us-west-2. Prices as of 2026-10-31.
Scheduling it off outside business hours cuts the 24/7 bill to roughly $353/mo — an estimated saving of up to $833/mo.
Cheapest on-demand
$1.6240/hr
us-east-1
Running 24/7
$1,186/mo
730-hour month
Business-hours savings
$833/mo
up to 70% off the 24/7 bill (est.)
How much does g5.4xlarge cost in each region?
| Region | Hourly (on-demand) | Spot (typical) | ≈ Monthly (24/7) |
|---|---|---|---|
| us-east-1 Cheapest | $1.6240/hr | $0.6821/hr | ≈ $1,186/mo |
| us-east-2 | $1.6240/hr | $0.6334/hr | ≈ $1,186/mo |
| us-west-2 | $1.6240/hr | $0.5359/hr | ≈ $1,186/mo |
| eu-west-1 | $1.8129/hr | $0.8158/hr | ≈ $1,323/mo |
| ap-south-1 | $1.9501/hr | $0.6630/hr | ≈ $1,424/mo |
| eu-central-1 | $2.0308/hr | $0.8529/hr | ≈ $1,482/mo |
| ap-southeast-2 | $2.1115/hr | $0.7390/hr | ≈ $1,541/mo |
| ap-northeast-1 | $2.3553/hr | $0.8950/hr | ≈ $1,719/mo |
| sa-east-1 | $2.7605/hr | $0.5521/hr | ≈ $2,015/mo |
How much does a schedule save on g5.4xlarge?
| Schedule | Monthly cost | Savings vs 24/7 |
|---|---|---|
| Running 24/7 | $1,186/mo | baseline |
| Weekdays only (off on weekends) | $847/mo | -$339/mo (29%) |
| Business hours only (10×5) | $353/mo | -$833/mo (70%) |
Assumes a 730-hour month at on-demand list price. Actual savings depend on when the instance is used.
About the g5 family
G5 steps up to NVIDIA A10G GPUs, aimed at heavier ML inference, mid-size training, and graphics workloads that outgrow the T4. Teams reach for it when a g4dn box stops keeping up, but the usage pattern doesn't change: active during working hours, fully idle the rest of the week — and at a higher hourly rate, every idle hour costs more.
Regional pricing varies: g5.4xlarge runs $1.6240/hr in us-east-1, the cheapest region priced here, versus $2.7605/hr in sa-east-1, the priciest — a 41% spread across regions for the identical instance type.
The next size up in the same family, g5.8xlarge (32 vCPU / 128 GB RAM), costs about $1,787/mo running 24/7 at its cheapest region — roughly 51% more than g5.4xlarge's ~$1,186/mo — for 2x the vCPU. GPU count stays the same (1).
Common questions
How much does g5.4xlarge cost per hour?
On AWS, g5.4xlarge costs from $1.624/hr on-demand, in us-east-1. The rate varies by region, and the table above lists each one. Indicative spot pricing starts near $0.5359/hr in us-west-2, and spot capacity can be reclaimed by the provider.
What are the g5.4xlarge specs?
g5.4xlarge is part of the g5 family on AWS and has 16 vCPUs, 64 GB of memory and 1× NVIDIA A10G.
How much does an idle g5.4xlarge cost per month?
At the cheapest listed region (us-east-1), a g5.4xlarge costs $1.6240/hr, or about $1,186/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 up to about $833/mo (70%) versus running 24/7. A lighter schedule — on around the clock on weekdays, off on weekends — still saves about $339/mo (29%).
When is g5 worth the premium over g4dn?
When the model or batch size outgrows the T4's 16 GB of GPU memory or its throughput — the A10G raises GPU memory to 24 GB and roughly doubles the compute. If a g4dn box is merely slow at training runs you do twice a week, scheduling beats upgrading: premium hardware only pays for itself while it is actually busy.
Other g5 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 2026-10-31. 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.