🐢 : GPT4 extremely slow on GPT4 API and ChatGPT

Hi, my GPT-4 API calls have been extremely slow since today. I am experiencing the same issue with ChatGPT (GPT-4). It seems to be linked to my account because when I test the speed using another account, GPT-4 responds normally. I haven’t reached the maximum quota for this month. Could it be related to a quota issue? Are there any other possible reasons?

Thanks for your help

The same here. Timeout every times after 5min. I need to launch 5 times to get 1 and i pay for 5, really amazing ! What is your plan to solve that OPENAI ?

1 Like

Yup, this is happening to me as well. Also seems to be specifically connected to my account.

1 Like

They have issues in their servers, I don’t work for OpenAI but it usually happens when they release new features, and plugins probably got everyone excited and got jumping on, which uses GPT4 in the background.

I hope they solve it soon.

1 Like

Yes, it was happening to me also. So I changed my backend response to SSE (Server send events) so that my users should know that something is going on.

1 Like

Overall average today for GPT-4 is 30s, but a few spikes around 6 minutes:


Impressive! May I ask where you obtained this data from?

1 Like

This is from the monitor in AWS hooked to the Lambda function that makes calls to the GPT-4 API.

So my own personal view of performance from my API calls.

1 Like

Here’s our API performance for GPT-3.5-turbo over the last month:

The data are somewhat noisy, but clearly an upwards trend. The type of inference hasn’t changed and the size of each request hasn’t changed.


I wonder what the solution is, especially if you sre trying to build a business around it.

Well, it’s not clear that there is a solution yet.
I’m hoping the OpenAI folks will pull through.
I’d be OK paying, say, 10x more for a 4x faster product with some kind of latency guarantee.

I’m also looking at other models, both self-hosted, and competing providers, but it’s somewhat slim pickings for now … Especially until Google actually lets people use that PaLM model they “released” twice already.

Clearly, there’s demand for what OpenAI are doing, and the main challenge is meeting up to that demand.

1 Like

Greetings! I use GPT 4 along with Dall e 3 for creating artistic images. Lately, I’ve noticed that it’s awfully slow. I thought it was due to the long chat I’m having creating my next project, but I see I’m not the only one this happens to. Once I enter the prompt I have to log out to log back in and see the response. In addition, at the beginning it offered 2 images among the results, but it has been limited to one per request in recent weeks. Limewire and Bing also support dall e 3, but it is not the same as using GPT 4 support.

I’m out OpenAI! You ask 20$ for a *** slow service. It’s not even a service anymore since almost all queries fail.