Rely on default OpenAI model for examples and tests

examples/canonical-metrics/bot.py

@@ -72,7 +72,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/chatbot-audio-recording/bot.py

@@ -95,7 +95,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/deployment/flyio-example/bot.py

@@ -53,7 +53,7 @@ async def main(room_url: str, token: str):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/deployment/modal-example/bot.py

@@ -43,7 +43,7 @@ async def main(room_url: str, token: str):
         api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/deployment/pipecat-cloud-example/bot.py

@@ -61,7 +61,7 @@ async def main(room_url: str, token: str):
         api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/02-llm-say-one-thing.py

@@ -38,7 +38,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/05-sync-speech-and-image.py

@@ -85,7 +85,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     # Create an HTTP session for API calls
     async with aiohttp.ClientSession() as session:
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         tts = CartesiaHttpTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/05a-local-sync-speech-and-image.py

@@ -93,7 +93,7 @@ async def main():
                         self.frame = frame
                     await self.push_frame(frame, direction)
 
-            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
             tts = CartesiaHttpTTSService(
                 api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/06-listen-and-respond.py

@@ -73,7 +73,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     ml = MetricsLogger()
 

examples/foundational/06a-image-sync.py

@@ -91,7 +91,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07-interruptible.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07a-interruptible-vad.py

@@ -44,7 +44,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07c-interruptible-deepgram.py

@@ -42,7 +42,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07d-interruptible-elevenlabs.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07e-interruptible-playht-http.py

@@ -46,7 +46,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07e-interruptible-playht.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         params=PlayHTTTSService.InputParams(language=Language.EN),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07g-interruptible-openai.py

@@ -46,7 +46,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07h-interruptible-openpipe.py

@@ -50,7 +50,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     llm = OpenPipeLLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
-        model="gpt-4.1",
         tags={"conversation_id": f"pipecat-{timestamp}"},
     )
 

examples/foundational/07i-interruptible-xtts.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             base_url="http://localhost:8000",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07j-interruptible-gladia.py

@@ -54,7 +54,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
 
     messages = [
         {

examples/foundational/07k-interruptible-lmnt.py

@@ -42,7 +42,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07m-interruptible-polly.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         params=PollyTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07o-interruptible-assemblyai.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07p-interruptible-krisp.py

@@ -44,7 +44,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07q-interruptible-rime-http.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07q-interruptible-rime.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="rex",
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07t-interruptible-fish.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07v-interruptible-neuphonic.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07w-interruptible-fal.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07x-interruptible-local.py

@@ -45,7 +45,7 @@ async def main():
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/10-wake-phrase.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/11-sound-effects.py

@@ -93,7 +93,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/12b-describe-video-gpt-4o.py

@@ -74,7 +74,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
     # OpenAI GPT-4o for vision analysis
-    openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/14-function-calling.py

@@ -53,7 +53,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.

examples/foundational/14d-function-calling-video.py

@@ -82,7 +82,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("get_weather", get_weather)
     llm.register_function("get_image", get_image)
 

examples/foundational/15-switch-voices.py

@@ -83,7 +83,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="a0e99841-438c-4a64-b679-ae501e7d6091",  # Barbershop Man
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("switch_voice", switch_voice)
 
     tools = [

examples/foundational/15a-switch-languages.py

@@ -73,7 +73,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="d4db5fb9-f44b-4bd1-85fa-192e0f0d75f9",  # Spanish-speaking Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("switch_language", switch_language)
 
     tools = [

examples/foundational/16-gpu-container-local-bot.py

@@ -54,7 +54,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         llm = OpenAILLMService(
             # To use OpenAI
             # api_key=os.getenv("OPENAI_API_KEY"),
-            # model="gpt-4.1"
             # Or, to use a local vLLM (or similar) api server
             model="meta-llama/Meta-Llama-3-8B-Instruct",
             base_url="http://0.0.0.0:8000/v1",

examples/foundational/17-detect-user-idle.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/20a-persistent-context-openai.py

@@ -185,7 +185,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # you can either register a single function for all function calls, or specific functions
     # llm.register_function(None, fetch_weather_from_api)

examples/foundational/22-natural-conversation.py

@@ -56,7 +56,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but it was easier as an example because we
     # leverage the context aggregators.
-    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     statement_messages = [
         {
@@ -69,7 +69,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
 
     # This is the regular LLM.
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/22b-natural-conversation-proposal.py

@@ -224,10 +224,10 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # This is the LLM that will be used to detect if the user has finished a
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but we have the machinery to use an LLM, so we might as well!
-    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # This is the regular LLM.
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)

examples/foundational/22c-natural-conversation-mixed-llms.py

@@ -428,16 +428,10 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # This is the LLM that will be used to detect if the user has finished a
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but we have the machinery to use an LLM, so we might as well!
-    statement_llm = AnthropicLLMService(
+    statement_llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
-        api_key=os.getenv("ANTHROPIC_API_KEY"),
-        model="claude-3-5-sonnet-20241022",
-    )
 
     # This is the regular LLM.
-    llm = OpenAILLMService(
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4.1",
-    )
     # Register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)

examples/foundational/23-bot-background-sound-daily.py

@@ -62,7 +62,7 @@ async def main():
             voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/23-bot-background-sound-p2p.py

@@ -69,7 +69,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/24-stt-mute-filter.py

@@ -64,7 +64,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("get_current_weather", fetch_weather_from_api)
 
     weather_function = FunctionSchema(

examples/foundational/28-transcription-processor.py

@@ -109,10 +109,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4.1",
-    )
 
     messages = [
         {

examples/foundational/29-livekit-audio-chat.py

@@ -127,7 +127,7 @@ async def main():
             ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/30-observer.py

@@ -88,7 +88,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/35-pattern-pair-voice-switching.py

@@ -120,7 +120,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     )
 
     # Initialize LLM
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # System prompt for storytelling with voice switching
     system_prompt = """You are an engaging storyteller that uses different voices to bring stories to life.

examples/foundational/36-user-email-gathering.py

@@ -63,7 +63,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     #     aiohttp_session=session,
     # )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # You can aslo register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("store_user_emails", store_user_emails)

examples/moondream-chatbot/bot.py

@@ -156,7 +156,7 @@ async def main():
             voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         ta = TalkingAnimation()
 

examples/patient-intake/bot.py

@@ -324,7 +324,7 @@ async def main():
         #     voice_id="846d6cb0-2301-48b6-9683-48f5618ea2f6",  # Spanish-speaking Lady
         # )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = []
         context = OpenAILLMContext(messages=messages)

examples/phone-chatbot/bot_twilio.py

@@ -60,7 +60,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/phone-chatbot/call_transfer.py

@@ -305,7 +305,7 @@ async def main(
     tools = ToolsSchema(standard_tools=[terminate_call_function, dial_operator_function])
 
     # Initialize LLM
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # Register functions with the LLM
     llm.register_function(

examples/phone-chatbot/simple_dialin.py

@@ -129,7 +129,7 @@ async def main(
     system_instruction = """You are Chatbot, a friendly, helpful robot. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by introducing yourself. If the user ends the conversation, **IMMEDIATELY** call the `terminate_call` function. """
 
     # Initialize LLM
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # Register functions with the LLM
     llm.register_function("terminate_call", terminate_call)

examples/phone-chatbot/simple_dialout.py

@@ -101,7 +101,7 @@ async def main(
     system_instruction = """You are Chatbot, a friendly, helpful robot. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by introducing yourself. If the user ends the conversation, **IMMEDIATELY** call the `terminate_call` function. """
 
     # Initialize LLM
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # Register functions with the LLM
     llm.register_function("terminate_call", terminate_call)

examples/sentry-metrics/bot.py

@@ -63,7 +63,6 @@ async def main():
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4.1",
             metrics=SentryMetrics(),
         )
 

examples/simple-chatbot/server/bot-openai.py

@@ -155,7 +155,7 @@ async def main():
         )
 
         # Initialize LLM service
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/telnyx-chatbot/bot.py

@@ -48,7 +48,7 @@ async def run_bot(
         ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 

examples/translation-chatbot/bot.py

@@ -150,7 +150,7 @@ async def main():
         in_language = "English"
         out_language = "Spanish"
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
         context = OpenAILLMContext()
         context_aggregator = llm.create_context_aggregator(context)
 

examples/twilio-chatbot/bot.py

@@ -68,7 +68,7 @@ async def run_bot(websocket_client: WebSocket, stream_sid: str, testing: bool):
         ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"), audio_passthrough=True)
 

examples/twilio-chatbot/client.py

@@ -98,7 +98,7 @@ async def run_client(client_name: str, server_url: str, duration_secs: int):
         ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # We let the audio passthrough so we can record the conversation.
     stt = DeepgramSTTService(

examples/websocket-server/bot.py

@@ -91,7 +91,7 @@ async def main():
         )
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 

tests/integration/test_integration_unified_function_calling.py

@@ -80,7 +80,7 @@ async def _test_llm_function_calling(llm: LLMService):
 @pytest.mark.skipif(os.getenv("OPENAI_API_KEY") is None, reason="OPENAI_API_KEY is not set")
 @pytest.mark.asyncio
 async def test_unified_function_calling_openai():
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4.1")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # This will fail if an exception is raised
     await _test_llm_function_calling(llm)