diff --git a/README.md b/README.md
index 7732114..6b40ead 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,9 @@ When the client sends a request with `gpt_refine=True`, this feature will be act
 - For `/v1/audio/transcriptions`, submit using `curl <api_url> -F file=audio.mp4 -F gpt_refine=True`.
 - For `/v1/konele/ws` and `/v1/konele/post`, use the URL format `/v1/konele/ws/gpt_refine`.
 
-The default model is `gpt-4o-mini`. You can easily edit the code to change the or LLM's prompt to better fit your workflow. It's just a few lines of code. Give it a try, it's very simple!
+The default model is `gpt-4o-mini` set by environment variable `OPENAI_LLM_MODEL`.
+
+You can easily edit the code LLM's prompt to better fit your workflow. It's just a few lines of code. Give it a try, it's very simple!
 
 ## Usage
 
diff --git a/whisper_fastapi.py b/whisper_fastapi.py
index 5ee6cc2..5991f3a 100644
--- a/whisper_fastapi.py
+++ b/whisper_fastapi.py
@@ -81,7 +81,7 @@ async def gpt_refine_text(
             os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1")
             + "/chat/completions",
             json={
-                "model": "gpt-4o-mini",
+                "model": os.environ.get("OPENAI_LLM_MODEL", "gpt-4o-mini"),
                 "temperature": 0.1,
                 "stream": False,
                 "messages": [