Overview

Inference hooks let organization owners and admins attach custom HTTP endpoints that run immediately before and after LLM inference. Pre-hooks can inspect and mutate the request body; post-hooks can inspect and mutate the final response. This page focuses on the admin API for configuring hooks. For a detailed explanation of hook behavior, payload format, and signature verification, see Security: Inference Hooks.

Base URL

Endpoints

Authentication

All endpoints require a Clerk JWT and organization owner or admin role.

Get configuration

Set configuration

If no hook secret exists, one is generated automatically and returned in the response.

Remove configuration

Request body fields

Error codes