g4dn.8xlarge pricing on AWS, and what idle time costs
g4dn.8xlarge is an AWS instance with 32 vCPUs, 128 GB of memory and 1× NVIDIA T4. It costs from $2.176/hr on-demand in us-east-1, about $1,588/mo running 24/7, and indicative spot pricing starts near $0.6528/hr in us-east-1. Prices as of 2026-10-31.
Scheduling it off outside business hours cuts the 24/7 bill to roughly $473/mo — an estimated saving of up to $1,116/mo.
Cheapest on-demand
$2.1760/hr
us-east-1
Running 24/7
$1,588/mo
730-hour month
Business-hours savings
$1,116/mo
up to 70% off the 24/7 bill (est.)
How much does g4dn.8xlarge cost in each region?
| Region | Hourly (on-demand) | Spot (typical) | ≈ Monthly (24/7) |
|---|---|---|---|
| us-east-1 Cheapest | $2.1760/hr | $0.6528/hr | ≈ $1,588/mo |
| us-east-2 | $2.1760/hr | $0.8486/hr | ≈ $1,588/mo |
| us-west-2 | $2.1760/hr | $0.7834/hr | ≈ $1,588/mo |
| ap-south-1 | $2.3950/hr | $1.0059/hr | ≈ $1,748/mo |
| eu-west-1 | $2.4260/hr | $1.0674/hr | ≈ $1,771/mo |
| eu-central-1 | $2.7200/hr | $1.1152/hr | ≈ $1,986/mo |
| ap-southeast-2 | $2.8300/hr | $1.0188/hr | ≈ $2,066/mo |
| ap-northeast-1 | $2.9380/hr | $1.2046/hr | ≈ $2,145/mo |
| ap-southeast-1 | $3.0450/hr | $0.9439/hr | ≈ $2,223/mo |
| sa-east-1 | $3.6980/hr | $0.7026/hr | ≈ $2,700/mo |
How much does a schedule save on g4dn.8xlarge?
| Schedule | Monthly cost | Savings vs 24/7 |
|---|---|---|
| Running 24/7 | $1,588/mo | baseline |
| Weekdays only (off on weekends) | $1,135/mo | -$454/mo (29%) |
| Business hours only (10×5) | $473/mo | -$1,116/mo (70%) |
Assumes a 730-hour month at on-demand list price. Actual savings depend on when the instance is used.
About the g4dn family
G4dn pairs NVIDIA T4 GPUs with Intel Cascade Lake vCPUs, the workhorse choice for ML inference, small-scale training, video transcoding, and cloud gaming or virtual workstations. It's also the default GPU dev box: a data scientist spins one up to prototype a model, then it sits idle every night and weekend while still billing for the GPU — the single most expensive kind of forgotten instance we see.
Regional pricing varies: g4dn.8xlarge runs $2.1760/hr in us-east-1, the cheapest region priced here, versus $3.6980/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, g4dn.12xlarge (48 vCPU / 192 GB RAM), costs about $2,856/mo running 24/7 at its cheapest region — roughly 80% more than g4dn.8xlarge's ~$1,588/mo — for 1.5x the vCPU. It also steps up to 4 GPUs from 1.
Common questions
How much does g4dn.8xlarge cost per hour?
On AWS, g4dn.8xlarge costs from $2.176/hr on-demand, in us-east-1. The rate varies by region, and the table above lists each one. Indicative spot pricing starts near $0.6528/hr in us-east-1, and spot capacity can be reclaimed by the provider.
What are the g4dn.8xlarge specs?
g4dn.8xlarge is part of the g4dn family on AWS and has 32 vCPUs, 128 GB of memory and 1× NVIDIA T4.
How much does an idle g4dn.8xlarge cost per month?
At the cheapest listed region (us-east-1), a g4dn.8xlarge costs $2.1760/hr, or about $1,588/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 $1,116/mo (70%) versus running 24/7. A lighter schedule — on around the clock on weekdays, off on weekends — still saves about $454/mo (29%).
Do I still pay for the GPU when a g4dn instance is stopped?
No — a stopped instance accrues no compute charges at all, GPU included; you keep paying only for its EBS volumes. That is exactly why the lease model pays off fastest on GPU boxes: the hardware premium disappears the moment the machine stops, and the environment survives on its EBS volumes — just don't stage anything you need on the local NVMe scratch drives, which do not survive a stop.
Other g4dn 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.