diff --git a/moderation.go b/moderation.go
index ff789a6..b386ddb 100644
--- a/moderation.go
+++ b/moderation.go
@@ -5,10 +5,23 @@ import (
 	"net/http"
 )
 
+// The moderation endpoint is a tool you can use to check whether content complies with OpenAI's usage policies.
+// Developers can thus identify content that our usage policies prohibits and take action, for instance by filtering it.
+
+// The default is text-moderation-latest which will be automatically upgraded over time.
+// This ensures you are always using our most accurate model.
+// If you use text-moderation-stable, we will provide advanced notice before updating the model.
+// Accuracy of text-moderation-stable may be slightly lower than for text-moderation-latest.
+const (
+	ModerationTextStable = "text-moderation-stable"
+	ModerationTextLatest = "text-moderation-latest"
+	ModerationText001    = "text-moderation-001"
+)
+
 // ModerationRequest represents a request structure for moderation API.
 type ModerationRequest struct {
-	Input string  `json:"input,omitempty"`
-	Model *string `json:"model,omitempty"`
+	Input string `json:"input,omitempty"`
+	Model string `json:"model,omitempty"`
 }
 
 // Result represents one of possible moderation results.
diff --git a/moderation_test.go b/moderation_test.go
index 3535bc8..2c11456 100644
--- a/moderation_test.go
+++ b/moderation_test.go
@@ -34,7 +34,7 @@ func TestModerations(t *testing.T) {
 	// create an edit request
 	model := "text-moderation-stable"
 	moderationReq := ModerationRequest{
-		Model: &model,
+		Model: model,
 		Input: "I want to kill them.",
 	}
 	_, err = client.Moderations(ctx, moderationReq)
@@ -77,7 +77,7 @@ func handleModerationEndpoint(w http.ResponseWriter, r *http.Request) {
 
 	res := ModerationResponse{
 		ID:    strconv.Itoa(int(time.Now().Unix())),
-		Model: *moderationReq.Model,
+		Model: moderationReq.Model,
 	}
 	res.Results = append(res.Results, result)