I’m looking to share an embedded GPT Model that I’ve been working on after I was kind of inspired by the Paul Graham Model(https://paul-graham-gpt.vercel.app/) by Mckay Wrigley(https://twitter.com/mckaywrigley). The problem is that every API call costs money and Mckay Wrigley solved it by asking for people’s OpenAI API Key to talk to the model, which a lot of non-technical people don’t get. Also, I know you can put a limit on your OpenAI Account so your bill isn’t astronomical the next day but that kind of defeats the purpose of sharing it online. Hopefully, there’s a solution but if not I’ll just ask for API Keys too.
I think that this may be a violation of OpenAI’s terms of service:
Hope the helps.
I think other than charging people the only way would be ad revenue. I am trying to figure that out myself, I made an ad-blocker check, that blocks the chat box if they have an ad-blocker on (obviously there are always ways around that), but it seems okay at a minimal point of view since the majority of the public probably don’t know how to get around that anyway. My ad blocker creates a browser cookie, and also creates a small 1x1 pixel “mock” ad and then if it gets blocked it engages overlay so they can’t use the chat since it will cost money. I have been creating endless SEO optimized content as well to attempt to generate organic traffic. Of course Google is taking its sweet time with everything so it takes a lot longer than you’d normally think. Just gotta go through the process, make a good UI, good content, good SEO, good chat set-up, and then hope that the ad revenue pays for the tokens. It seemed too good to be true that Turbo came out at 10x cheaper than Davinci, although I can’t seem to make it work on my Davinci-003 model, so I am screwed on that part unfortunately. It’s a shame because I really like how my Davinci model is working out after many, many, many endless hours of programming and testing. Sigh.
Thanks for sharing. I will look into offsetting the cost with ads.