diff --git a/gpt3.go b/gpt3.go
index 7bd091c..b469f15 100644
--- a/gpt3.go
+++ b/gpt3.go
@@ -15,7 +15,28 @@
 //		Stop: []string{"You:"},
 //	}
 //
+//The content filter endpoint is used to validate a prompt in order to safeguard responses ushered back to the enduser.
+//The request object should always have the following parameters:
 //
+// reformattedPrompt := fmt.Sprintf("<|endoftext|>[%s]\n--\nLabel:", string(query))
+//
+// req := gpt3.ContentFilterRequest{
+//		Prompt:      reformattedPrompt,
+//		MaxTokens:   1,
+//		TopP:        0,
+//		Temperature: 0,
+//		Logprobs: 10,
+//	}
+//
+// The Response is the same format as that of the Completions request with the following entries:
+//
+// 0 => text is safe
+// 1 => This text is sensitive. This means that the text could be talking about a sensitive topic, something political,
+//		religious, or talking about a protected class such as race or nationality.
+// 2 => This text is unsafe. This means that the text contains profane language, prejudiced or hateful language,
+//      something that could be NSFW, or text that portrays certain groups/people in a harmful manner.
+//
+
 package gpt3
 
 import (