diff --git a/examples/foundational/07l-interruptible-groq.py b/examples/foundational/07l-interruptible-groq.py
index 208d39c2d..a4bfee8dc 100644
--- a/examples/foundational/07l-interruptible-groq.py
+++ b/examples/foundational/07l-interruptible-groq.py
@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GroqLLMService(
         api_key=os.getenv("GROQ_API_KEY"),
         settings=GroqLLMService.Settings(
-            model="meta-llama/llama-4-maverick-17b-128e-instruct",
+            model="llama-3.1-8b-instant",
             system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         ),
     )
diff --git a/examples/foundational/07n-interruptible-google-http.py b/examples/foundational/07n-interruptible-google-http.py
index 91e822ec0..35c80a972 100644
--- a/examples/foundational/07n-interruptible-google-http.py
+++ b/examples/foundational/07n-interruptible-google-http.py
@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.GoogleLLMSettings(
+        settings=GoogleLLMService.Settings(
             model="gemini-2.5-flash",
             # force a certain amount of thinking if you want it
             # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
diff --git a/examples/foundational/14j-function-calling-nvidia.py b/examples/foundational/14j-function-calling-nvidia.py
index 39b75b7ac..7dd772c03 100644
--- a/examples/foundational/14j-function-calling-nvidia.py
+++ b/examples/foundational/14j-function-calling-nvidia.py
@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
             # Recommended when turning thinking off
             temperature=0.0,
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            system_instruction="/no_think You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         ),
     )
     # You can also register a function_name of None to get all functions