diff --git a/server/app/config.py b/server/app/config.py
index 880c04d..587d4b0 100644
--- a/server/app/config.py
+++ b/server/app/config.py
@@ -4,13 +4,14 @@ from pydantic_settings import BaseSettings
 class Settings(BaseSettings):
     nvidia_api_key: str
     app_password: str
-    nvidia_base_url: str = "https://integrate.api.nvidia.com/v1"
-    nvidia_model: str = "nvidia/nemotron-3-ultra-550b-a55b"
-    nvidia_timeout_seconds: int = 120
-    nvidia_max_tokens: int = 16384
-    nvidia_temperature: float = 1.0
-    nvidia_top_p: float = 0.95
-    nvidia_reasoning_budget: int = 2048
+    nvidia_base_url: str
+    nvidia_model: str
+    nvidia_timeout_seconds: int
+    nvidia_max_tokens: int
+    nvidia_temperature: float
+    nvidia_top_p: float
+    nvidia_reasoning_budget: int
+    nvidia_enable_thinking: bool
 
     model_config = {"env_file": ".env"}
 
diff --git a/server/app/main.py b/server/app/main.py
index 2c9534c..5a78dbd 100644
--- a/server/app/main.py
+++ b/server/app/main.py
@@ -68,7 +68,7 @@ async def generate_recipes(request: RecipeRequest):
                 top_p=settings.nvidia_top_p,
                 max_tokens=settings.nvidia_max_tokens,
                 extra_body={
-                    "chat_template_kwargs": {"enable_thinking": True},
+                    "chat_template_kwargs": {"enable_thinking": settings.nvidia_enable_thinking},
                     "reasoning_budget": settings.nvidia_reasoning_budget,
                 },
                 stream=True,