Gpt-3-turbo slow vs chatgpt 3 website

[dan2]

how can i get the same performace, seems like its slow like gpt4 takes over 30 sec for a response to finish all the text and its not that long.

[sps]

We proved the API is intentionally slow

Closing this for now, to answer the OP’s question: No, we do not make the API slow intentionally. I spend north of 10 hours a day, 6+ days a week advocating for and building things for developers inside of OpenAI. We would never intentionally slow things down. The API is not running with the exact same setup as ChatGPT is which is why you see a different response time. You are also likely using a shared engine which makes things much slower and less predictable.

[dan2]

Still. My prompt is 400 tokens and the output is the same. Takes 30 secs for the output. A json to return using gpt3 api.
How can I get the same speed as chatgpt3?

[bgokce]

I have the same problem, left support ticket many times but no response for 1 week.

[BrianLovesAI]

Try ‘text-davinci-002’ for using the API to achieve the same performance speed. However, it is unlikely that we can expect high accuracy when using this model.