Rate limits

Limits

• The default is 600 requests per minute per key, counted in fixed one-minute windows.
• Your balance is the other limit: each request reserves its largest possible cost, so the number of requests you can run in parallel is bounded by your available credits.
• Need more? Contact @avenrotech on X with your expected volume.

Headers

Every chat completion response to a valid key, including a 429, carries:

• x-ratelimit-limit-requests: requests allowed per minute for this key.
• x-ratelimit-remaining-requests: requests left in the current window.
• x-ratelimit-reset-requests: time until the window resets, such as 17s.

A request over the limit gets 429 rate_limit_exceeded with a retry-after header in seconds. It is not charged.