RPM rate limits at 100 when using assistants API

Using open AI python library we are calling assistant API functionality with code such as client.beta.threads.create, messages.create, runs.create, etc

We are frequently running into error code: 429: “you’ve exceeded the 100 request/min rate limit, please slow down and try again.”

Our account is tier 4 which i believe has a 10,000 RPM limit so I am trying to figure out why we are getting this error. In the meantime we have implemented tenacity and such but with the amount of traffic we are getting this does not seem tenable.

Can someone from openAI take a look and see what is going on?

What is going on is that Assistants is beta, and is rate limited by the number of calls to the API endpoints, account-wide. It is not suitable for volume deployment, both because of the artificial limits, and because of the lack of cost accountability and controls.

You actually seem to be showing an increase from 60 requests per minute that is documented.

https://platform.openai.com/docs/assistants/how-it-works/limitations

1 Like

That must be it. Thanks. Wish this was clearer in the documentation.