Rate Limits

Throughput guidance for fair and stable OptimAI Search usage.

Design clients to be steady rather than bursty.

Client behavior

  • Keep concurrency bounded.
  • Retry only when the error is retryable.
  • Back off when the API returns 429.
  • Avoid sending duplicate requests for the same user action.

Known client limits

These are validation limits in the MCP server and SDK, not a promise of an account quota:

Client settingAllowed rangeDefault
MCP query length1–1,000 characters
Blocking MCP timeout10–55 seconds45 seconds
MCP poll interval500–10,000 milliseconds2,000 milliseconds
MCP list page size1–100 records10
x402 completion timeout300,000 milliseconds
x402 poll interval2,000 milliseconds

Product behavior

Show the user that retrieval is in progress. If a request is delayed, keep source and status context visible instead of hiding the wait.

Exact account quotas and partner policies are enforced by the backend and may vary by plan or environment. For create retries, use a unique idempotency key; reusing a key with a changed route, body, or Search mode returns a conflict.