Which is cheaper, Modal Nvidia L4 or RunPod L4 · Secure Cloud?

RunPod L4 · Secure Cloud, at $0.490/GPU-hr against $0.799/GPU-hr, both the on-demand rate for one GPU for one hour, read on 17 Sept 2026. On the whole machine that is $0.49/hr against $0.80/hr.

Which holds more GPU memory?

Both add up to 24 GB across the instance, at 24 GB and 24 GB a board.

What would a week cost?

$134 for Modal Nvidia L4 and $82 for RunPod L4 · Secure Cloud, at 168 hours of the whole machine at its published rate, with no commitment discount. Neither publishes an interruptible rate.

What does the hourly price leave out?

Modal Nvidia L4: disk none, billed separately, no regions published, billed per second. RunPod L4 · Secure Cloud: disk none, billed separately, no regions published, billed per second. Egress and tax are extra on both.

Modal Nvidia L4 vs RunPod L4 · Secure Cloud.

machine vs machine · prices as of 17 Sept 2026

The same L4 at two providers, so the board is identical and everything else is not. RunPod L4 · Secure Cloud takes 2 of 4 rounds against Modal Nvidia L4. It is also the cheaper of the two by the hour, at $0.490/GPU-hr against $0.799/GPU-hr.

Modal

Nvidia L4

$0.799/GPU-hr

$0.80/hr for the machine · $134 a week

1x L4 · 24 GB each · $0.0333/GB-hr · Serverless

Modal ↗

RunPodwins 2 rounds

L4 · Secure Cloud

$0.490/GPU-hr

$0.49/hr for the machine · $82 a week

1x L4 · 24 GB each · $0.0204/GB-hr

RunPod ↗

Price per GPU-hour (lower wins)

$0.799/GPU-hr

$0.490/GPU-hr

Interruptible rate (lower wins)

not published

Price per GB of VRAM (lower wins)

$0.0333/GB-hr

$0.0204/GB-hr

VRAM per GPU

24 GB

GPUs per instance

1x L4

vCPU

not stated

RAM

not stated

50 GB

Included storage

none · volumes extra

Regions listed

regions not stated

What a run costs on each

An hour of the machine$0.80/hr vs $0.49/hr
A day$19 vs $12
A week$134 vs $82
A week on spotnot published vs not published

Modal then RunPod, at the published rate with no commitment discount

Go further

open in the compare tool →

Add a third or fourth machine, or switch the weighting, in the tool.

Frequently asked

Which is cheaper, Modal Nvidia L4 or RunPod L4 · Secure Cloud?: RunPod L4 · Secure Cloud, at $0.490/GPU-hr against $0.799/GPU-hr, both the on-demand rate for one GPU for one hour, read on 17 Sept 2026. On the whole machine that is $0.49/hr against $0.80/hr.
Which holds more GPU memory?: Both add up to 24 GB across the instance, at 24 GB and 24 GB a board.
What would a week cost?: $134 for Modal Nvidia L4 and $82 for RunPod L4 · Secure Cloud, at 168 hours of the whole machine at its published rate, with no commitment discount. Neither publishes an interruptible rate.
What does the hourly price leave out?: Modal Nvidia L4: disk none, billed separately, no regions published, billed per second. RunPod L4 · Secure Cloud: disk none, billed separately, no regions published, billed per second. Egress and tax are extra on both.

Every rate is the on-demand price for one GPU for one hour, read 17 Sept 2026 from each provider's own page, so a node of eight is compared at what one of its GPUs costs. Storage, egress and tax are extra unless a row says otherwise, and reserved or committed rates are not indexed. Bars are scaled to the larger value in each row.