How do I calculate the cost of my last execution on a serverless GPU?
For example if I have one GPU with cost $0.00016 and the other ones with $0.00019. How do I know which serverless GPU actually picked this GPU after the request has been completed? Also, is there an easy way to just get the cost of the last
runsync
request instead of manually calculating it?2 Replies
you can return your gpu type, in your handler you add some function to read from environmental variable
like so: (an example)
RUNPOD_GPU_NAME=NVIDIA+RTX+4000+Ada+Generation
no there's no way of getting cost of a runsync request
code to get the gpu model name like above:
Ah, thanks.