Simultaneous Request Limitations

Hi there,

I am interested in using the API at scale and I have some questions around that topic. I am aware of the rate limits found here: Is API usage subject to any rate limits? | OpenAI Help Center

My question is: For my API token, are there limits around the number of simultaneous requests I can make as long as I am under the request per minute rate limit?

For instance can I make a call every N seconds in parallel with the same API token as long as I stay under the request rate limit?

Thanks!

1 Like

Hello,
Have you found an answer ?
I am also wondering about simultaneous requests
Thanks!

Hi @cabo ,
It seems there s no limitation : Simultaneous Requests - API
:grinning:

@youri.rd

Thanks for finding this answer!

@cabo @youri.rd , it looks like there is indeed no limitation on simultaneous requests. However, it is not clear to me how to keep track of what response belongs to what request as there doesn’t seem to be a way to attach a unique identifier to a request. Any thoughts or suggestions on how to address that problem? Thanks!

@vleu Probably be good to start a new topic describing your issue and what technology you are using. Most usage waits for response to come back (or stream to finish).