diff --git a/specification/cognitiveservices/OpenAI.Inference/models/chat.completions.tsp b/specification/cognitiveservices/OpenAI.Inference/models/chat.completions.tsp
index 0333f1635dae..6c93e8aa0463 100644
--- a/specification/cognitiveservices/OpenAI.Inference/models/chat.completions.tsp
+++ b/specification/cognitiveservices/OpenAI.Inference/models/chat.completions.tsp
@@ -49,6 +49,14 @@ model ChatCompletionsOptions {
   @projectedName("json", "max_tokens")
   maxTokens?: int32;
 
+  @doc("""
+    Information about the content filtering category (hate, sexual, violence, self_harm), if it 
+    has been detected, as well as the severity level (very_low, low, medium, high-scale that 
+    determines the intensity and risk level of harmful content) and if it has been filtered or not.
+    """)
+  @projectedName("json","contentFilterResults")
+  annotation?: string;
+
   @doc("""
     The sampling temperature to use that controls the apparent creativity of generated completions.
     Higher values will make output more random while lower values will make results more focused