diff --git a/examples/canonical-metrics/bot.py b/examples/canonical-metrics/bot.py
index 0d31f1df5..d14f4149e 100644
--- a/examples/canonical-metrics/bot.py
+++ b/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 = [
             {
diff --git a/examples/chatbot-audio-recording/bot.py b/examples/chatbot-audio-recording/bot.py
index 5fa6f5aaa..c3e20ecfe 100644
--- a/examples/chatbot-audio-recording/bot.py
+++ b/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 = [
             {
diff --git a/examples/deployment/flyio-example/bot.py b/examples/deployment/flyio-example/bot.py
index 83e058434..7e5bef3ee 100644
--- a/examples/deployment/flyio-example/bot.py
+++ b/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 = [
         {
diff --git a/examples/deployment/modal-example/bot.py b/examples/deployment/modal-example/bot.py
index 1c4423c10..327c6a5e4 100644
--- a/examples/deployment/modal-example/bot.py
+++ b/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 = [
         {
diff --git a/examples/deployment/pipecat-cloud-example/bot.py b/examples/deployment/pipecat-cloud-example/bot.py
index 4e2ddfbd4..d86c7f575 100644
--- a/examples/deployment/pipecat-cloud-example/bot.py
+++ b/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 = [
         {
diff --git a/examples/foundational/02-llm-say-one-thing.py b/examples/foundational/02-llm-say-one-thing.py
index 84651499b..94d2b27f7 100644
--- a/examples/foundational/02-llm-say-one-thing.py
+++ b/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 = [
         {
diff --git a/examples/foundational/05-sync-speech-and-image.py b/examples/foundational/05-sync-speech-and-image.py
index 2213089c8..9021dbf54 100644
--- a/examples/foundational/05-sync-speech-and-image.py
+++ b/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"),
diff --git a/examples/foundational/05a-local-sync-speech-and-image.py b/examples/foundational/05a-local-sync-speech-and-image.py
index 4a7b32ba7..77486d247 100644
--- a/examples/foundational/05a-local-sync-speech-and-image.py
+++ b/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"),
diff --git a/examples/foundational/06-listen-and-respond.py b/examples/foundational/06-listen-and-respond.py
index 9d197d3e3..c41c39748 100644
--- a/examples/foundational/06-listen-and-respond.py
+++ b/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()
 
diff --git a/examples/foundational/06a-image-sync.py b/examples/foundational/06a-image-sync.py
index 17f42578e..8ebe5400c 100644
--- a/examples/foundational/06a-image-sync.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07-interruptible.py b/examples/foundational/07-interruptible.py
index 34b24a748..a94dfad4b 100644
--- a/examples/foundational/07-interruptible.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07a-interruptible-vad.py b/examples/foundational/07a-interruptible-vad.py
index af1e64916..a146ad636 100644
--- a/examples/foundational/07a-interruptible-vad.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07c-interruptible-deepgram-vad.py b/examples/foundational/07c-interruptible-deepgram-vad.py
index 118b46ec3..366644be6 100644
--- a/examples/foundational/07c-interruptible-deepgram-vad.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07c-interruptible-deepgram.py b/examples/foundational/07c-interruptible-deepgram.py
index 6b5cdcce0..12081480d 100644
--- a/examples/foundational/07c-interruptible-deepgram.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07d-interruptible-elevenlabs-http.py b/examples/foundational/07d-interruptible-elevenlabs-http.py
index 42590254d..4984897bc 100644
--- a/examples/foundational/07d-interruptible-elevenlabs-http.py
+++ b/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 = [
             {
diff --git a/examples/foundational/07d-interruptible-elevenlabs.py b/examples/foundational/07d-interruptible-elevenlabs.py
index 27dd5cd72..fe31c12b7 100644
--- a/examples/foundational/07d-interruptible-elevenlabs.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07e-interruptible-playht-http.py b/examples/foundational/07e-interruptible-playht-http.py
index c7d18083a..394fff2ce 100644
--- a/examples/foundational/07e-interruptible-playht-http.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07e-interruptible-playht.py b/examples/foundational/07e-interruptible-playht.py
index 952ff0a76..a1b5dddf9 100644
--- a/examples/foundational/07e-interruptible-playht.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07g-interruptible-openai.py b/examples/foundational/07g-interruptible-openai.py
index 931b5fc5e..3bc019ad1 100644
--- a/examples/foundational/07g-interruptible-openai.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07h-interruptible-openpipe.py b/examples/foundational/07h-interruptible-openpipe.py
index 4574198aa..633e0cf15 100644
--- a/examples/foundational/07h-interruptible-openpipe.py
+++ b/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}"},
     )
 
diff --git a/examples/foundational/07i-interruptible-xtts.py b/examples/foundational/07i-interruptible-xtts.py
index a4ae4f2be..aa64425fd 100644
--- a/examples/foundational/07i-interruptible-xtts.py
+++ b/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 = [
             {
diff --git a/examples/foundational/07j-interruptible-gladia.py b/examples/foundational/07j-interruptible-gladia.py
index 1d526db48..4ed903ea6 100644
--- a/examples/foundational/07j-interruptible-gladia.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07k-interruptible-lmnt.py b/examples/foundational/07k-interruptible-lmnt.py
index 65129e7ce..092e4758f 100644
--- a/examples/foundational/07k-interruptible-lmnt.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07m-interruptible-polly.py b/examples/foundational/07m-interruptible-polly.py
index 83b13fbaa..6fe09619d 100644
--- a/examples/foundational/07m-interruptible-polly.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07o-interruptible-assemblyai.py b/examples/foundational/07o-interruptible-assemblyai.py
index 2302aa97c..137060651 100644
--- a/examples/foundational/07o-interruptible-assemblyai.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07p-interruptible-krisp.py b/examples/foundational/07p-interruptible-krisp.py
index 399f52f3b..1f650363e 100644
--- a/examples/foundational/07p-interruptible-krisp.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07q-interruptible-rime-http.py b/examples/foundational/07q-interruptible-rime-http.py
index df2166d69..c5dedf63a 100644
--- a/examples/foundational/07q-interruptible-rime-http.py
+++ b/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 = [
             {
diff --git a/examples/foundational/07q-interruptible-rime.py b/examples/foundational/07q-interruptible-rime.py
index 8d836ba01..3df39ef6c 100644
--- a/examples/foundational/07q-interruptible-rime.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07t-interruptible-fish.py b/examples/foundational/07t-interruptible-fish.py
index a5827a704..160bbddaf 100644
--- a/examples/foundational/07t-interruptible-fish.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07v-interruptible-neuphonic-http.py b/examples/foundational/07v-interruptible-neuphonic-http.py
index a1f57d5f4..f1db00454 100644
--- a/examples/foundational/07v-interruptible-neuphonic-http.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07v-interruptible-neuphonic.py b/examples/foundational/07v-interruptible-neuphonic.py
index f566c285c..25df4e2e6 100644
--- a/examples/foundational/07v-interruptible-neuphonic.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07w-interruptible-fal.py b/examples/foundational/07w-interruptible-fal.py
index 26e22f2bf..6c1b71937 100644
--- a/examples/foundational/07w-interruptible-fal.py
+++ b/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 = [
         {
diff --git a/examples/foundational/07x-interruptible-local.py b/examples/foundational/07x-interruptible-local.py
index bc9620cec..5027e8bcb 100644
--- a/examples/foundational/07x-interruptible-local.py
+++ b/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 = [
         {
diff --git a/examples/foundational/10-wake-phrase.py b/examples/foundational/10-wake-phrase.py
index 8b0b746e7..4fb19343d 100644
--- a/examples/foundational/10-wake-phrase.py
+++ b/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 = [
         {
diff --git a/examples/foundational/11-sound-effects.py b/examples/foundational/11-sound-effects.py
index 5a900f78a..4a70d15d1 100644
--- a/examples/foundational/11-sound-effects.py
+++ b/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"),
diff --git a/examples/foundational/12b-describe-video-gpt-4o.py b/examples/foundational/12b-describe-video-gpt-4o.py
index 7958edabc..c676390cc 100644
--- a/examples/foundational/12b-describe-video-gpt-4o.py
+++ b/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"),
diff --git a/examples/foundational/14-function-calling.py b/examples/foundational/14-function-calling.py
index fbc2e11e8..31a6417f4 100644
--- a/examples/foundational/14-function-calling.py
+++ b/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.
diff --git a/examples/foundational/14d-function-calling-video.py b/examples/foundational/14d-function-calling-video.py
index a3840ca2d..e51dc96dd 100644
--- a/examples/foundational/14d-function-calling-video.py
+++ b/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)
 
diff --git a/examples/foundational/15-switch-voices.py b/examples/foundational/15-switch-voices.py
index cf93d8858..14aeab76a 100644
--- a/examples/foundational/15-switch-voices.py
+++ b/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 = [
diff --git a/examples/foundational/15a-switch-languages.py b/examples/foundational/15a-switch-languages.py
index 2b9449242..de89721db 100644
--- a/examples/foundational/15a-switch-languages.py
+++ b/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 = [
diff --git a/examples/foundational/16-gpu-container-local-bot.py b/examples/foundational/16-gpu-container-local-bot.py
index 16ea36cf1..4853764fc 100644
--- a/examples/foundational/16-gpu-container-local-bot.py
+++ b/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",
diff --git a/examples/foundational/17-detect-user-idle.py b/examples/foundational/17-detect-user-idle.py
index 1bed5361a..2f1652a0f 100644
--- a/examples/foundational/17-detect-user-idle.py
+++ b/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 = [
         {
diff --git a/examples/foundational/20a-persistent-context-openai.py b/examples/foundational/20a-persistent-context-openai.py
index 07a94a944..bba3fc00e 100644
--- a/examples/foundational/20a-persistent-context-openai.py
+++ b/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)
diff --git a/examples/foundational/22-natural-conversation.py b/examples/foundational/22-natural-conversation.py
index f53ea551c..0878d4831 100644
--- a/examples/foundational/22-natural-conversation.py
+++ b/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 = [
         {
diff --git a/examples/foundational/22b-natural-conversation-proposal.py b/examples/foundational/22b-natural-conversation-proposal.py
index feae4c922..b6e89556f 100644
--- a/examples/foundational/22b-natural-conversation-proposal.py
+++ b/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)
diff --git a/examples/foundational/22c-natural-conversation-mixed-llms.py b/examples/foundational/22c-natural-conversation-mixed-llms.py
index dc24565d6..e6b0d0df7 100644
--- a/examples/foundational/22c-natural-conversation-mixed-llms.py
+++ b/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(
-        api_key=os.getenv("ANTHROPIC_API_KEY"),
-        model="claude-3-5-sonnet-20241022",
-    )
+    statement_llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_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"))
     # 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)
diff --git a/examples/foundational/23-bot-background-sound-daily.py b/examples/foundational/23-bot-background-sound-daily.py
index f0a298bcc..97947d768 100644
--- a/examples/foundational/23-bot-background-sound-daily.py
+++ b/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 = [
             {
diff --git a/examples/foundational/23-bot-background-sound-p2p.py b/examples/foundational/23-bot-background-sound-p2p.py
index b046f2e83..f18c58971 100644
--- a/examples/foundational/23-bot-background-sound-p2p.py
+++ b/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 = [
         {
diff --git a/examples/foundational/24-stt-mute-filter.py b/examples/foundational/24-stt-mute-filter.py
index 66dbb1267..98f054143 100644
--- a/examples/foundational/24-stt-mute-filter.py
+++ b/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(
diff --git a/examples/foundational/28-transcription-processor.py b/examples/foundational/28-transcription-processor.py
index ee49e35f9..42e31d5f6 100644
--- a/examples/foundational/28-transcription-processor.py
+++ b/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(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4.1",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {
diff --git a/examples/foundational/29-livekit-audio-chat.py b/examples/foundational/29-livekit-audio-chat.py
index bf22db4c7..b8d44deb7 100644
--- a/examples/foundational/29-livekit-audio-chat.py
+++ b/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"),
diff --git a/examples/foundational/30-observer.py b/examples/foundational/30-observer.py
index 98a794c3a..ad11f2267 100644
--- a/examples/foundational/30-observer.py
+++ b/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 = [
         {
diff --git a/examples/foundational/35-pattern-pair-voice-switching.py b/examples/foundational/35-pattern-pair-voice-switching.py
index 63ca604e1..aadbe0cc3 100644
--- a/examples/foundational/35-pattern-pair-voice-switching.py
+++ b/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.
diff --git a/examples/foundational/36-user-email-gathering.py b/examples/foundational/36-user-email-gathering.py
index 767584740..39958ce79 100644
--- a/examples/foundational/36-user-email-gathering.py
+++ b/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)
diff --git a/examples/moondream-chatbot/bot.py b/examples/moondream-chatbot/bot.py
index ec19f3de4..87bc7e5fc 100644
--- a/examples/moondream-chatbot/bot.py
+++ b/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()
 
diff --git a/examples/patient-intake/bot.py b/examples/patient-intake/bot.py
index fba48531e..64bb11743 100644
--- a/examples/patient-intake/bot.py
+++ b/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)
diff --git a/examples/phone-chatbot/bot_twilio.py b/examples/phone-chatbot/bot_twilio.py
index 2022bd8f0..9f7740320 100644
--- a/examples/phone-chatbot/bot_twilio.py
+++ b/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 = [
         {
diff --git a/examples/phone-chatbot/call_transfer.py b/examples/phone-chatbot/call_transfer.py
index ccb762efa..487391c67 100644
--- a/examples/phone-chatbot/call_transfer.py
+++ b/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(
diff --git a/examples/phone-chatbot/simple_dialin.py b/examples/phone-chatbot/simple_dialin.py
index faa6a9d4f..dee51f865 100644
--- a/examples/phone-chatbot/simple_dialin.py
+++ b/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)
diff --git a/examples/phone-chatbot/simple_dialout.py b/examples/phone-chatbot/simple_dialout.py
index 08610c760..6b15d3af8 100644
--- a/examples/phone-chatbot/simple_dialout.py
+++ b/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)
diff --git a/examples/sentry-metrics/bot.py b/examples/sentry-metrics/bot.py
index 452d47c6e..853911f2b 100644
--- a/examples/sentry-metrics/bot.py
+++ b/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(),
         )
 
diff --git a/examples/simple-chatbot/server/bot-openai.py b/examples/simple-chatbot/server/bot-openai.py
index 23aee786d..70f813f52 100644
--- a/examples/simple-chatbot/server/bot-openai.py
+++ b/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 = [
             {
diff --git a/examples/telnyx-chatbot/bot.py b/examples/telnyx-chatbot/bot.py
index a568ca150..861aa1c7a 100644
--- a/examples/telnyx-chatbot/bot.py
+++ b/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"))
 
diff --git a/examples/translation-chatbot/bot.py b/examples/translation-chatbot/bot.py
index 93e1c93c8..b7611e3a3 100644
--- a/examples/translation-chatbot/bot.py
+++ b/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)
 
diff --git a/examples/twilio-chatbot/bot.py b/examples/twilio-chatbot/bot.py
index f2cf02e8e..9b1501aaf 100644
--- a/examples/twilio-chatbot/bot.py
+++ b/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)
 
diff --git a/examples/twilio-chatbot/client.py b/examples/twilio-chatbot/client.py
index 6142e25b1..97cca0cd0 100644
--- a/examples/twilio-chatbot/client.py
+++ b/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(
diff --git a/examples/websocket-server/bot.py b/examples/websocket-server/bot.py
index ebd72a336..2f08f8b43 100644
--- a/examples/websocket-server/bot.py
+++ b/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"))
 
diff --git a/tests/integration/test_integration_unified_function_calling.py b/tests/integration/test_integration_unified_function_calling.py
index a8155e957..09611fd3a 100644
--- a/tests/integration/test_integration_unified_function_calling.py
+++ b/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)