Baseten L4 24 GiB vs Modal Nvidia L4.
machine vs machine · prices as of
The same L4 at two providers, so the board is identical and everything else is not. Modal Nvidia L4 takes 2 of 4 rounds against Baseten L4 24 GiB. It is also the cheaper of the two by the hour, at $0.799/GPU-hr against $0.848/GPU-hr.
L4 24 GiB
$0.848/GPU-hr
$0.85/hr for the machine · $143 a week
1x L4 · 24 GB each · $0.0354/GB-hr · Serverless
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
Price per GPU-hour (lower wins)
$0.848/GPU-hr
$0.799/GPU-hr
Interruptible rate (lower wins)
not published
not published
Price per GB of VRAM (lower wins)
$0.0354/GB-hr
$0.0333/GB-hr
VRAM per GPU
24 GB
24 GB
GPUs per instance
1x L4
1x L4
vCPU
not stated
not stated
RAM
not stated
not stated
Included storage
not stated
none · volumes extra
Regions listed
regions not stated
regions not stated
What a run costs on each
- An hour of the machine$0.85/hr vs $0.80/hr
- A day$20 vs $19
- A week$143 vs $134
- A week on spotnot published vs not published
Baseten then Modal, at the published rate with no commitment discount
Go further
Add a third or fourth machine, or switch the weighting, in the tool.
Frequently asked
- Which is cheaper, Baseten L4 24 GiB or Modal Nvidia L4?
- Modal Nvidia L4, at $0.799/GPU-hr against $0.848/GPU-hr, both the on-demand rate for one GPU for one hour, read on 17 Sept 2026. On the whole machine that is $0.80/hr against $0.85/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?
- $143 for Baseten L4 24 GiB and $134 for Modal Nvidia L4, 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?
- Baseten L4 24 GiB: disk not stated, no regions published, billed per minute. Modal Nvidia L4: 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.