diff --git a/backend/ai_generator.py b/backend/ai_generator.py
index 0363ca90c..149cb46e1 100644
--- a/backend/ai_generator.py
+++ b/backend/ai_generator.py
@@ -34,10 +34,13 @@ def __init__(self, api_key: str, model: str):
         self.model = model
         
         # Pre-build base API parameters
+        # Sonnet 5 rejects non-default sampling params, and runs adaptive
+        # thinking when `thinking` is omitted - disabled here to keep answers
+        # fast and to leave the full max_tokens budget for the response.
         self.base_params = {
             "model": self.model,
-            "temperature": 0,
-            "max_tokens": 800
+            "max_tokens": 800,
+            "thinking": {"type": "disabled"}
         }
     
     def generate_response(self, query: str,
diff --git a/backend/config.py b/backend/config.py
index d9f6392ef..c4ba3712b 100644
--- a/backend/config.py
+++ b/backend/config.py
@@ -10,7 +10,7 @@ class Config:
     """Configuration settings for the RAG system"""
     # Anthropic API settings
     ANTHROPIC_API_KEY: str = os.getenv("ANTHROPIC_API_KEY", "")
-    ANTHROPIC_MODEL: str = "claude-sonnet-4-20250514"
+    ANTHROPIC_MODEL: str = "claude-sonnet-5"
     
     # Embedding model settings
     EMBEDDING_MODEL: str = "all-MiniLM-L6-v2"