I missed the announcement, I think, but it appears you can now use a total of 4,000 tokens - split evenly between prompt and output. This should help chat bots and some other applications. Thanks to the OpenAI team! Keep it up!

New 4,000 token context window (prompt+output)

PaulBellow March 17, 2022, 8:47pm 2

tokens

2 Likes

Provide technical updates via email listserv (or something)

Topic		Replies	Views
Is the "output (Maximum length)" for the GPT-4-1106-preview API still capped at 4095? API gpt-4 , gpt-4-turbo	3	7639	November 15, 2023
Why is gpt-3.5-turbo-1106 max_tokens limited to 4096? API	3	14137	January 11, 2024
Context window size for the babbage-002 model Documentation question , fine-tuning , api	3	353	June 15, 2024
Maximum token allowed for chat gpt model gpt 3.5 turbo API chatgpt	3	2755	February 15, 2024
Test new 128k window on gpt-4-1106-preview API	29	18435	February 6, 2024