RunPod RTX 4090 · Community Cloud vs RunPod RTX A6000 · Community Cloud.
machine vs machine · prices as of
Two machines from RunPod's own catalogue, the nearest to each other on price. RunPod RTX A6000 · Community Cloud takes 3 of 4 rounds against RunPod RTX 4090 · Community Cloud. It is also the cheaper of the two by the hour, at $0.330/GPU-hr against $0.340/GPU-hr.
RTX 4090 · Community Cloud
$0.340/GPU-hr
$0.34/hr for the machine · $57 a week
1x RTX 4090 · 24 GB each · $0.0142/GB-hr · Marketplace
RTX A6000 · Community Cloud
$0.330/GPU-hr
$0.33/hr for the machine · $55 a week
1x RTX A6000 · 48 GB each · $0.0069/GB-hr · Marketplace
Price per GPU-hour (lower wins)
$0.340/GPU-hr
$0.330/GPU-hr
Interruptible rate (lower wins)
not published
not published
Price per GB of VRAM (lower wins)
$0.0142/GB-hr
$0.0069/GB-hr
VRAM per GPU
24 GB
48 GB
GPUs per instance
1x RTX 4090
1x RTX A6000
vCPU
6
9
RAM
41 GB
50 GB
Included storage
none · volumes extra
none · volumes extra
Regions listed
regions not stated
regions not stated
What a run costs on each
- An hour of the machine$0.34/hr vs $0.33/hr
- A day$8.16 vs $7.92
- A week$57 vs $55
- A week on spotnot published vs not published
RunPod then RunPod, 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, RunPod RTX 4090 · Community Cloud or RunPod RTX A6000 · Community Cloud?
- RunPod RTX A6000 · Community Cloud, at $0.330/GPU-hr against $0.340/GPU-hr, both the on-demand rate for one GPU for one hour, read on 17 Sept 2026. On the whole machine that is $0.33/hr against $0.34/hr.
- Which holds more GPU memory?
- RunPod RTX A6000 · Community Cloud, at 48 GB across the instance against 24 GB. Per board it is 24 GB against 48 GB.
- What would a week cost?
- $57 for RunPod RTX 4090 · Community Cloud and $55 for RunPod RTX A6000 · Community 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?
- RunPod RTX 4090 · Community Cloud: disk none, billed separately, no regions published, billed per second. RunPod RTX A6000 · Community 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.