R
RunPod7mo ago
Rodka

Serverless GPU Pricing

Hello. I chose a 24 GiB configuration with the following GPUs: L4, RTXA5000, and RTX3090. I ran some benchmarks and noticed that using only RTX3090 is better for my use-case (faster execution times and so on). Is the base pricing for all these 3 GPUs the same? That is, supposing for a moment that the delay times and execution times are the same across all GPUs, will the billing result in the same value regardless of the one I choose?
8 Replies
nerdylive
nerdylive7mo ago
if they're in the same class then yes look at the endpoint settings, theres the price for them they are grouped Some gpus with higher or lower vram has different pricings
Rodka
RodkaOP7mo ago
OK. That's what I thought; just wanted to make sure. Many thanks.
nerdylive
nerdylive7mo ago
No problem happy to help
frank
frank4mo ago
For instance one active worker per month would cost (16GB GPU): $0,00012x3600x24x30 = $311,04 Correct @nerdylive ?
nerdylive
nerdylive4mo ago
i usually count it like: base price (active) (1s): $0.00012 / S times 60s (1m): ($0.0072 / M) 1m* 60(1h): ($0.432 / H) (i assume 730h/mo) so times 730: ... 315.36 yeah around that
frank
frank4mo ago
Thanks a lot @nerdylive super quick! Do you think that if I ping the endpoint periodically (with no actual computation, just to keep it warm), like every N minutes, the pricing could be lower while still having a warm endpoint? with ping I mean a payload that contains no job and makes the function end immediately
nerdylive
nerdylive4mo ago
hmm sure try it
frank
frank4mo ago
I'll and let you know!
Want results from more Discord servers?
Add your server