← Glossary / 80 of 100
n. / Cost and performance
Rate limit
Definition
A rate limit is a cap a provider sets on how many requests or tokens you may use in a period. When you exceed it, calls are rejected, usually with an HTTP 429 error.
In more detail
Limits are often per minute, per model and per account tier. Agents hit them easily because one user request can trigger many model calls at once. Handle them with retries that wait, queues that smooth bursts and fallbacks to another model, and watch the count of 429 errors in traces.
Example
Ten agents start at the same moment and each makes five model calls. Provider limits allow 30 requests a minute, so 20 calls come back with 429.
Related terms
