kriyam.aistudioAPI reference

Rate limits & credits

How many calls a key can make, and when you're charged for one.

Rate limits and credits

Each key is limited to 60 requests per minute by default, and every response carries X-RateLimit-Limit and X-RateLimit-Remaining. Over the limit you get a 429 with Retry-After. Support can raise a key's limit without a deploy, so read the real figure off the key rather than assuming this one.

Runs are charged to the account's credit balance. A run that is refused is never charged, and a tool that fails outright is not charged either.