[sokoloff]

Don’t overlook the possibility to use your own physical hardware, running high-end commodity graphics cards (2080Ti, Titan RTX), especially for model training. (I haven’t found this to be overly effort or time intensive and the payoff is enormous on a dollars-basis.)

You didn’t give enough details for someone to get really specific. I’m assuming from your text that the issue is inference not training costs, in which case there’s some great advice already posted, but more details might help.