Limits & Quotas
Golem AI enforces limits to ensure platform stability and prevent runaway costs.Audit time budgets
Each mode has a fixed task budget; the agent is force-stopped before the wall-clock expires so reporting always completes:
Even when a run hits its budget, you receive everything confirmed before the cutoff — the audit completes with a coverage summary showing what was and wasn’t finished.
API rate limits
Sensitive endpoints are rate-limited per client to prevent abuse:- Verification attempts (app drafts and apps): 6 per minute
- Mobile store lookups: 30 per minute
- API key operations: low per-minute caps
429 responses and honor Retry-After headers.
Plan caps
Exceeding an app or asset limit returns a clear error on the create/update call.