jargon

Applied AI·The API layer

your calls start coming back 429 once traffic climbs, and what you are hitting is requests per minute or tokens per minute, not a bug in your code.

Rate limits (RPM, TPM)

Draft summary, pending review

Provider caps on requests per minute and tokens per minute, usually tiered by spend. Production code treats 429 responses as normal weather, not as errors to page on.

Commonly confused with