GPT-4 API costs $0.03-$0.12/1000 tokens (the top for prompt tokens on the 8k context option, the top for response tokens on the 32k context option, and response on 8k and prompt on 32k are $0.06/1000), so best case about 33,000 tokens/$. tokens:words is about 4:3, so that’s about 25,000 words/$, not 375,000 words/$.
(Practically, you aren’t going to get quite the ideal even on the 8k context option because you are going to use at least some response tokens on each request, though I would imagine text -> software controls can be optimized so that the response is fairly token-efficient in most cases.)
Also, GPT-4 API access is in limited-access with a waitlist that is advertised as prioritized based on submitting AI evaluation cases to OpenAI’s repository.
(Practically, you aren’t going to get quite the ideal even on the 8k context option because you are going to use at least some response tokens on each request, though I would imagine text -> software controls can be optimized so that the response is fairly token-efficient in most cases.)
Also, GPT-4 API access is in limited-access with a waitlist that is advertised as prioritized based on submitting AI evaluation cases to OpenAI’s repository.