Update app.py

app.py

@@ -18,7 +18,7 @@ HF_TOKEN = os.getenv("HF_TOKEN", "")
 # Use TinyLlama - Small, fast, and reliable  
 MODEL_NAME = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 # Use HuggingFace Inference API
-API_URL = f"https://api-inference.huggingface.co/models/{MODEL_NAME}"
+API_URL = f"https://router.huggingface.co/hf-inference/models/{MODEL_NAME}"
 
 def query_hf_model(prompt: str, max_tokens: int = 1000, temperature: float = 0.7, stream: bool = False):
     """Query Hugging Face Inference API"""