Restrictions on how many API requests you can make per minute/hour/day. Providers impose rate limits to prevent server overload and ensure fair access. Limits typically apply per API key and can restrict requests per minute (RPM) and tokens per minute (TPM).
Why it matters
Rate limits are the invisible ceiling you hit when scaling AI applications. They're why batch processing matters, why you need retry logic, and why some providers charge more for higher rate limits.