Requests-per-minute and tokens-per-minute ceilings apply per API key, set from your plan when the key is created. Exact figures for your account aren't shown here yet — contact us if a request is being rate-limited.

No per-model limits are configured on your plan.

Going over your monthly spend cap or running out of balance blocks every API key on this account until you add credit, request a higher cap, or the month resets. A rate limit only rejects the requests that exceed it — normal traffic resumes on its own once you're back under it.