Hello Fellow Members,
I am running into a issue where i am using chatgpt-4o-latest api with max token set to 16k. In the prompt i have asked the response must be atleast 1600words or near that range. But whenever I make the call response is getting throttled to around 800-900 words max.
total token size of prompt is 3k, I guese it still have 13k left to respond but not sure why its not following the directions.
Same prompt when ran in webapp with same model it does return rich response and follows the direction.
Any idea how to fix this?