Platform Limits
Sandbox Agent Limits
Code runtime and managed loop agents have separate limits for compute time (sandbox execution):Sandbox agent limits are separate from direct LLM agent limits. You can use both with their respective quotas.
Paid Calls
Paid agent calls (where credits are charged) bypass free tier daily limits and use a separate abuse protection cap of 100,000 calls/day. This prevents paid usage from being blocked by free tier limits.How Limits Are Counted
Top-Level Calls
Each call to an agent counts as 1 call against your daily limit:Orchestrator Calls
When you call an orchestrator that calls other agents, only the top-level call counts:Rate Limit Headers
Every response includes headers showing your limit status:Rate Limit Errors
When you exceed your limit:Timeouts
Request Timeouts
Authors set timeout in their manifest:
Timeout Propagation
For orchestrators, timeouts propagate through the call chain:TIMEOUT.
Composition Limits
Max Hops
Limits how deep agent-to-agent calls can go:min(caller's max_hops, agent's max_hops)
Downstream Cap
Controls the budget passed to each downstream dependency call. This limits what each called agent can spend in further downstream calls — it does not limit the current agent’s own call count:Handling Rate Limits
Check Before Calling
Implement Backoff
JavaScript Example
Upgrading Limits
Pro Plan
- 10,000 calls/day
- 50 concurrent requests
- Priority support
Enterprise
- Custom limits
- SLA guarantees
- Dedicated support
Service Limits
Always-on services have separate limits from on-demand agent runs:
Service compute time is metered by runtime minutes and counts toward your workspace usage. See Billing for details.
Best Practices
- Check remaining calls before batch operations
- Implement exponential backoff for 429 responses
- Cache responses when appropriate
- Use webhooks instead of polling when available
- Monitor usage in the dashboard