diff --git a/slack_bot/slack_bot/models/__init__.py b/slack_bot/slack_bot/models/__init__.py
index 6ca66ca8..12898151 100644
--- a/slack_bot/slack_bot/models/__init__.py
+++ b/slack_bot/slack_bot/models/__init__.py
@@ -1,7 +1,7 @@
 from .base import ResponseModel
 from .chat_completion import ChatCompletionAzure, ChatCompletionOpenAI
 from .hello import Hello
-from .llama_index import LlamaIndexGPTAzure, LlamaIndexGPTOpenAI, LlamaIndexHF
+from .llama import LlamaIndexGPTAzure, LlamaIndexGPTOpenAI, LlamaIndexHF
 
 # Please ensure that any models needing OPENAI_API_KEY are named *openai*
 # Please ensure that any models needing OPENAI_AZURE_API_BASE and OPENAI_AZURE_API_KEY are named *azure*
diff --git a/slack_bot/slack_bot/models/llama_index.py b/slack_bot/slack_bot/models/llama.py
similarity index 98%
rename from slack_bot/slack_bot/models/llama_index.py
rename to slack_bot/slack_bot/models/llama.py
index d28c8882..eba2e416 100644
--- a/slack_bot/slack_bot/models/llama_index.py
+++ b/slack_bot/slack_bot/models/llama.py
@@ -361,7 +361,7 @@ def __init__(self, *args: Any, **kwargs: Any) -> None:
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
         self.temperature = 0.7
         super().__init__(
-            *args, model_name="gpt-3.5-turbo-16k", max_input_size=16384, **kwargs
+            *args, model_name="gpt-3.5-turbo", max_input_size=16384, **kwargs
         )
 
     def _prep_llm(self) -> LLM:
@@ -390,7 +390,7 @@ def __init__(self, *args: Any, **kwargs: Any) -> None:
         self.openai_api_version = "2023-03-15-preview"
         self.temperature = 0.7
         super().__init__(
-            *args, model_name="gpt-3.5-turbo-16k", max_input_size=16384, **kwargs
+            *args, model_name="gpt-3.5-turbo", max_input_size=16384, **kwargs
         )
 
     def _prep_llm(self) -> LLM: