Limits & quotas

To keep the service stable and costs predictable, requests are subject to the following limits.

Account concurrency

Each account has a cap on requests in flight at the same time (set by the administrator). Beyond it you get 429; wait for in-flight requests to finish or ask the administrator for a higher cap.

Key limits

Each API key can be configured in the dashboard with:

Subscription allowances

Keys in subscription groups are limited by the plan's daily / weekly / monthly allowance.

Free models

Free models have their own rate limits, described in the model catalog.

Request size

Request bodies have a size limit; compress large files such as images first. Oversized requests are rejected.

Checking current usage

Call GET https://zzq.si/v1/usage or open the key usage lookup to see the key's quota and usage.