diff --git a/app/llm.py b/app/llm.py
index 817bbfe..6777e5e 100644
--- a/app/llm.py
+++ b/app/llm.py
@@ -240,7 +240,9 @@ class LLM:
                 params["max_completion_tokens"] = self.max_tokens
             else:
                 params["max_tokens"] = self.max_tokens
-                params["temperature"] = temperature or self.temperature
+                params["temperature"] = (
+                    temperature if temperature is not None else self.temperature
+                )
 
             if not stream:
                 # Non-streaming request
@@ -379,7 +381,9 @@ class LLM:
                 params["max_completion_tokens"] = self.max_tokens
             else:
                 params["max_tokens"] = self.max_tokens
-                params["temperature"] = temperature or self.temperature
+                params["temperature"] = (
+                    temperature if temperature is not None else self.temperature
+                )
 
             response = await self.client.chat.completions.create(**params)