05 · Getting Models to Act
Rate Limit
A cap on how much you can call
A cap on how many requests or tokens you can send in a window of time, set by the provider to manage load. Hit it and your calls get throttled or refused.
Concrete example
A free tier might allow a few requests per minute; production apps pay for much higher ceilings.
Why it matters
Shapes how a product is architected — and what it costs to scale to many users.