GPT-3.5-TURBO response time is extremely long sometimes north of > 1 minute for a simple prompt.
I switch to other models and everything works fine. Even GPT-4 is faster.
I get this error message: Request failed with status code 502
Has this been an issue only over the past few days or have you always experienced this with GPT-3.5-TURBO?
I was finding the Chrome was locking up when a 504 was returned so I added a curl timeout which has fixed the hanging but I do often receive the error.
I’d be curious to hear recommendations. The timeout duration, re-processing ideas etc.
curl_setopt($curl, CURLOPT_TIMEOUT, 30);
if (curl_errno($curl)) {
$error_message = curl_error($curl);
echo “A network error occurred as a response was not received within 30 seconds.”;
} else {
Definitely been a few days of slow responses, but today is especially bad. Half my requests are failing because of gpt-3.5-turbo long response times for my serverless functioons.
Same! Today is super slow. Sometimes randomly its fast but usually very slow and many timeouts
I’m having the same issue with GpT-3.5
“name”: “Timeout”,
“message”: “Request timed out: HTTPSConnectionPool(host=‘api.openai.com’, port=443): Read timed out. (read timeout=600)”,
Same here, seeing about 5% of the requests from my application time out. Started yesterday for me.
same here for both gpt-3.5-turbo and text-davinci-003
API is almost non usable for the last 2 hours??? OpenAI please look into this asap.
Same here unfortunately. It’s especially bad today. I hope response times gets improved.
The performance has been significantly slower since yesterday, and it appears that OpenAI may not be aware of the issue yet. Completing a request is currently taking around 5 minutes.
I am also experiencing this issue too. My requests timeout inconsistently
"Something went wrong. If this issue persists please contact us through our help center at help.openai.com. "
I’m getting this for the last 1 hr, won’t even respond to my friendly “Hi” lol
Not sure what’s going on…
Have been having the same issue over the last 12 hours.
Looks like the website is now down completely. I just get a white and empty page.
Same here. Really annoying. Does anybody know a workaround or faster / working model?
Same issue. Calls to API that took a few seconds three days ago now taking 5 minutes or more
I noticed some issues with the chat API as well. Often times reponse time is decent, but other times it fails on timeout. Horrible for user experience of course
https://api.openai.com/v1/chat/completions is taking between 2s and a 5-minute timeout