diff --git a/.env.example b/.env.example
index 68cb9d13..21c1030a 100644
--- a/.env.example
+++ b/.env.example
@@ -13,9 +13,9 @@ LLM_BINDING_HOST=http://host.docker.internal:11434
 LLM_MODEL=mistral-nemo:latest
 
 # Lollms example
-LLM_BINDING=lollms
-LLM_BINDING_HOST=http://host.docker.internal:9600
-LLM_MODEL=mistral-nemo:latest
+# LLM_BINDING=lollms
+# LLM_BINDING_HOST=http://host.docker.internal:9600
+# LLM_MODEL=mistral-nemo:latest
 
 
 # Embedding Configuration (Use valid host. For local services, you can use host.docker.internal)
diff --git a/lightrag/llm.py b/lightrag/llm.py
index 1f52d4ae..c7f51aea 100644
--- a/lightrag/llm.py
+++ b/lightrag/llm.py
@@ -622,11 +622,11 @@ async def nvidia_openai_complete(
 
 
 async def azure_openai_complete(
-    model: str = "gpt-4o-mini", prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> str:
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     result = await azure_openai_complete_if_cache(
-        model,
+        os.getenv("LLM_MODEL", "gpt-4o-mini"),
         prompt,
         system_prompt=system_prompt,
         history_messages=history_messages,