Rate limits

Per-key limits.

Rate limits are abuse protection, not a billing gate. They are applied per API key.

Tier	Default	Applies to
Standard	60 requests / minute	interpret, conversations, analyses (start), ingest, embed-tokens
Poll	600 requests / minute	GET /analyses/{id}

On exceeding a limit you get 429 rate_limited with a Retry-After header (seconds). The SDKs retry automatically when the error is retryable, respecting Retry-After.