All calculators
Reliability and durable execution
Rate limit throughput calculator
Find out how many agent runs and parallel agents your API rate limits allow, and whether requests or tokens are the bottleneck
Result
Parallel agents you can run
22
- Agent runs per hour
- 333
- Requests per minute allowed by RPM
- 500
- Requests per minute allowed by TPM
- 67
How it is calculated
Usable requests per minute = min(RPM, TPM / tokens per request). Runs per minute = usable requests / requests per run. Parallel agents = runs per minute × minutes per run.
Related service
Agent platform consultancy