Gateway

Create a rate limit policy

Creates a named policy with requests per minute, tokens per minute, or concurrent request limits. The gateway does not enforce rate limit policies yet; they are saved for the upcoming enforcement release.

post/rate-limits/policies

Request

  • Base URL: https://api.phaseo.app/v1
  • URL: https://api.phaseo.app/v1/rate-limits/policies
  • Auth: HTTP bearer

Request body

namestring required
descriptionstring nullable
requests_per_minuteinteger nullable

Requests allowed per minute. Null means requests are not limited.

tokens_per_minuteinteger nullable

Input and output tokens allowed per minute. Null means tokens are not limited.

concurrent_requestsinteger nullable

Requests allowed in flight at once. Null means concurrency is not limited.

fail_closedboolean

Reject requests when the limit cannot be checked, instead of allowing them. Adds latency to every request the policy covers.

Response

Rate limit policy created

Changes

No recorded changes to this operation across all 1 revision of this API.