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, generate, conversations, analyses (start), ingest, save version, read source, start & download exports, embed-tokens
Poll	600 requests / minute	cheap reads & polling: GET /analyses/{id}, GET /exports/{id}, project list & metadata, /hmi/values & /hmi/history

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.