From 847c70880f667f3b6479003fc931556e06c96eef Mon Sep 17 00:00:00 2001 From: "mintlify[bot]" <109931778+mintlify[bot]@users.noreply.github.com> Date: Tue, 27 Jan 2026 09:48:54 +0000 Subject: [PATCH] Update product/guardrails.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> --- product/guardrails.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/product/guardrails.mdx b/product/guardrails.mdx index b8458698..11d55352 100644 --- a/product/guardrails.mdx +++ b/product/guardrails.mdx @@ -601,7 +601,7 @@ This example corresponds to a `config` like: #### Streaming Responses -Portkey now supports hook results in streaming responses for `/chat/completions`, `/completions`, `/embeddings`, and `/messages` endpoints. This allows you to stop streaming or show redacted content if a request violates your guardrail policies, enabling clients to respect content policy guidelines in real-time. +For streaming requests, Portkey supports guardrails on the **input** (request) only—not on the streaming output. When an input guardrail runs on a streaming request, the hook results are now included in the streaming response, allowing clients to handle policy violations (e.g., stop streaming or show redacted content) in real-time. To receive hook results in streaming responses, you must set the `x-portkey-strict-open-ai-compliance` header to `false`.