# Problem with API request (long answer time)

**URL:** <https://community.openai.com/t/problem-with-api-request-long-answer-time/106996>\
**Category:** API\
**Created:** [March 19, 2023, 7:48pm UTC](https://community.openai.com/t/problem-with-api-request-long-answer-time/106996 "2023-03-19T19:48:13Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![dyzmas2021](https://avatars.discourse-cdn.com/v4/letter/d/eada6e/32.png) [@dyzmas2021](https://community.openai.com/u/dyzmas2021)\
**Post date:** [March 19, 2023, 7:48pm UTC](https://community.openai.com/t/problem-with-api-request-long-answer-time/106996/1 "2023-03-19T19:48:13Z")

</div>

We asking API and we have 30s delay in answer. Is it normal or something is wrong? Everything was OK till today

---

<div class="post-metadata">

**Author:** ![linus](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/linus/32/42486_2.png) [@linus](https://community.openai.com/u/linus)\
**Post date:** [March 19, 2023, 8:08pm UTC](https://community.openai.com/t/problem-with-api-request-long-answer-time/106996/2 "2023-03-19T20:08:16Z")

</div>

Hi @dyzmas2021,

you can check if there are outages [OpenAI Status](https://status.openai.com/) here.

But you are not the only one with this issue ( [Variable Response Times on API gpt-3.5-turbo - General API discussion - OpenAI API Community Forum](https://community.openai.com/t/variable-response-times-on-api-gpt-3-5-turbo/106802)) 🙂

---

<div class="post-metadata">

**Author:** ![Jeffers](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jeffers/32/49344_2.png) [@Jeffers](https://community.openai.com/u/Jeffers)\
**Post date:** [March 19, 2023, 9:23pm UTC](https://community.openai.com/t/problem-with-api-request-long-answer-time/106996/3 "2023-03-19T21:23:07Z")

</div>

I’m going to start monitoring the 3.5 Turbo response times across the server and when there are too many “curl\_setopt($curl, CURLOPT\_TIMEOUT, 30);” timeouts, I’ll revert to Davinci 003. or GPT4. It will be interesting to see how I can switch/convert the Turbo chat style resprequests into the completion style.

---

<div class="post-metadata">

**Author:** ![jandieg.b](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jandieg.b/32/209813_2.png) [@jandieg.b](https://community.openai.com/u/jandieg.b)\
**Post date:** [December 14, 2023, 5:24pm UTC](https://community.openai.com/t/problem-with-api-request-long-answer-time/106996/4 "2023-12-14T17:24:40Z")

</div>

I am having random timeouts on 3.5 (tolerance is 20 sec).

On 4 sometimes it even takes a minute to respond. Same prompt in 3.5 takes seconds.