Documentation menu
Reference / v0.1

Limits & availability

Build against the current release with explicit boundaries and predictable retries.

Reviewed September 16, 2026 · Current implementation

Current limits

LimitValue
Requests60 per minute per API key
Active API jobs5 per customer; 3 per endpoint
Endpoints per job1–100 explicit targets
Question length500 characters
Job timeout5–120 seconds; default 120
List page size1–100; default 50
Answer length4,000 characters
MCP request body32 KiB
MCP upstream response2 MiB

These are operational limits, not credits or billing allowances. On HTTP 429 honor Retry-After and use bounded retries. Authentication and MCP preflight checks also consume API requests; frequent polling is unnecessary.

Available now

  • Customer API keys and explicit scopes.
  • Endpoint discovery, asynchronous questions, attributed answers and cancellation through REST.
  • Six MCP tools through hosted Streamable HTTP or a local stdio adapter.
  • Stored-summary substring search and customer audit events.

Planned, not yet available

  • Hosted OAuth sign-in, Authfu integration, human memberships and invitations.
  • Site-scoped roles and keys, provider customer switching.
  • Webhook delivery, public SDK packages and self-service key issuance.
  • Endpoint action tools and automatic escalation to frontier models.
  • Cross-customer correlation or bulk combined evidence.
Continue readingTroubleshooting