diff --git a/lambda_function.py b/lambda_function.py
index 3132692..12d6b03 100644
--- a/lambda_function.py
+++ b/lambda_function.py
@@ -51,7 +51,16 @@ def process_event(event):
                     text = text.split(" ", 1)[1]
                     messages = [{"role": "user", "content": text}]
                     bot.send_chat_action(chat_id, "typing")
-                    response = escape_special_characters(create_conversation(messages))
+                    conversation = create_conversation(messages)
+                    content = escape_special_characters(conversation[0])
+                    model = conversation[1]
+                    tokens = conversation[2]
+                    response = (
+                        f"{content}\n\n"
+                        f"\-\-\-\-\-\-\-\-\-\- *Information* \-\-\-\-\-\-\-\-\-\-\n"
+                        f"Model: `{model}`\n"
+                        f"Tokens: `{tokens[0]}({tokens[1]}\+{tokens[2]})`"
+                    )
                     bot.reply_message(chat_id, message_id, response)
                 except IndexError:
                     bot.reply_message(chat_id, message_id, "请输入对话内容")
diff --git a/utils/chat.py b/utils/chat.py
index fc7c541..409c655 100644
--- a/utils/chat.py
+++ b/utils/chat.py
@@ -5,10 +5,17 @@ import openai
 openai.api_key = os.environ["OPENAI_API_KEY"]
 
 
-def create_conversation(messages: list) -> str:
+def create_conversation(messages: list):
     response = openai.ChatCompletion.create(
         model="gpt-3.5-turbo",
         messages=messages,
         temperature=1,
     )
-    return response["choices"][0]["message"]["content"]
+    content = response["choices"][0]["message"]["content"]
+    model = response["model"]
+    tokens = [
+        response["usage"]["total_tokens"],
+        response["usage"]["prompt_tokens"],
+        response["usage"]["completion_tokens"],
+    ]
+    return content, model, tokens