Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 import requests
 
-# Function to send your prompt to NVIDIA LLaMA 4 Scout
+# Function to send your prompt to NVIDIA LLaMA 4 Maverick
 def talk_to_llama(prompt):
-    url = "https://api.nvcf.nvidia.com/v1/messages"  # ✅ Correct endpoint
+    url = "https://integrate.api.nvidia.com/v1/meta/llama-4-maverick-17b-128e-instruct"
     headers = {
-        "Authorization": "Bearer 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",
+        "Authorization": "Bearer YOUR_API_KEY_HERE",  # Replace with your actual API key
         "Content-Type": "application/json"
     }
     data = {
@@ -23,8 +23,8 @@ chat = gr.Interface(
     fn=talk_to_llama,
     inputs="text",
     outputs="text",
-    title="Chat with LLaMA 4 Scout",
-    description="Ask anything! This chatbot uses NVIDIA’s 3.5M token LLaMA 4 Scout model."
+    title="Chat with LLaMA 4 Maverick",
+    description="Ask anything! This chatbot uses NVIDIA’s LLaMA 4 Maverick 17B 128E Instruct model."
 )
 
 chat.launch()