diff --git a/models.go b/models.go
index 1c0cc01..efe7c20 100644
--- a/models.go
+++ b/models.go
@@ -50,7 +50,7 @@ type ChatCompletionRequest struct {
 	Messages []ChatCompletionRequestMessage `json:"messages"`
 
 	// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic
-	Temperature float32 `json:"temperature,omitempty"`
+	Temperature *float32 `json:"temperature,omitempty"`
 
 	// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
 	TopP float32 `json:"top_p,omitempty"`