"max_tokens": 4096,

app.py

@@ -1135,7 +1135,7 @@ def generate_key_moments(formatted_simple_transcript, formatted_transcript):
     request_payload = {
         "model": "gpt-4-1106-preview",
         "messages": messages,
-        "max_tokens": 10000,
+        "max_tokens": 4096,
         "response_format": response_format
     }