Hi OP, I liked your project!
Doing something similar and I'm wondering what engines you are using?
Because mine is already charged 0.18$ for 200 requests.
Here is my current setup:
"max_tokens" => 150,
"temperature" => 0.6,
"top_p" => 1,
"frequency_penalty" => 1,
"presence_penalty" => 1,
model is text-davinci-003.
Can you let me know how you are only charged $10 for 40K requests?
Here is my current setup: "max_tokens" => 150, "temperature" => 0.6, "top_p" => 1, "frequency_penalty" => 1, "presence_penalty" => 1,
model is text-davinci-003.
Can you let me know how you are only charged $10 for 40K requests?