AI glossary
Rate limit
A rate limit caps how many requests or tokens you may send to an API in a period of time; past it, requests are refused until the window resets.
Model APIs often limit both requests per minute and tokens per minute. A refused call usually comes back with status 429 and sometimes a hint of when to try again.
The usual response is to retry with exponential backoff and some random jitter, so many clients do not all retry at the same moment.
Set your own limits too. A loop with a bug can spend a month's budget in an hour, and a per-user limit protects everyone else.
Learn it hands-on
These free lessons teach it with commands to run in a lab and checked tasks. Read them whole with no account.