How this calculator works
Enter requests per minute limit, tokens per minute limit, average tokens per request. Select Calculate to apply the displayed formula and review the labeled results.
Formula / method
Effective requests/minute = min(RPM limit, TPM limit ÷ average tokens/request)
Worked example
500 RPM and 200,000 TPM with 1,200-token requests permits about 166.67 requests/minute.
Assumptions and limitations
Requests have a stable average total token count.
Burst rules, concurrency, retries, output variability and separate input/output limits can reduce capacity.