diff --git a/letta/llm_api/azure_openai.py b/letta/llm_api/azure_openai.py
index dc2566b8..52cb6d3a 100644
--- a/letta/llm_api/azure_openai.py
+++ b/letta/llm_api/azure_openai.py
@@ -3,12 +3,6 @@ from collections import defaultdict
 import requests
 from openai import AzureOpenAI
 
-from letta.llm_api.openai import prepare_openai_payload
-from letta.schemas.llm_config import LLMConfig
-from letta.schemas.openai.chat_completion_response import ChatCompletionResponse
-from letta.schemas.openai.chat_completions import ChatCompletionRequest
-from letta.settings import ModelSettings
-
 
 def get_azure_chat_completions_endpoint(base_url: str, model: str, api_version: str):
     return f"{base_url}/openai/deployments/{model}/chat/completions?api-version={api_version}"
@@ -98,21 +92,3 @@ def azure_openai_get_embeddings_model_list(base_url: str, api_key: str, api_vers
     model_options = [m for m in model_list if valid_embedding_model(m)]
 
     return model_options
-
-
-def azure_openai_chat_completions_request(
-    model_settings: ModelSettings, llm_config: LLMConfig, chat_completion_request: ChatCompletionRequest
-) -> ChatCompletionResponse:
-    """https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions"""
-
-    assert model_settings.azure_api_key is not None, "Missing required api key field when calling Azure OpenAI"
-    assert model_settings.azure_api_version is not None, "Missing required api version field when calling Azure OpenAI"
-    assert model_settings.azure_base_url is not None, "Missing required base url field when calling Azure OpenAI"
-
-    data = prepare_openai_payload(chat_completion_request)
-    client = AzureOpenAI(
-        api_key=model_settings.azure_api_key, api_version=model_settings.azure_api_version, azure_endpoint=model_settings.azure_base_url
-    )
-    chat_completion = client.chat.completions.create(**data)
-
-    return ChatCompletionResponse(**chat_completion.model_dump())
diff --git a/letta/llm_api/llm_api_tools.py b/letta/llm_api/llm_api_tools.py
index 6a3abfe1..a511c722 100644
--- a/letta/llm_api/llm_api_tools.py
+++ b/letta/llm_api/llm_api_tools.py
@@ -13,7 +13,6 @@ from letta.llm_api.anthropic import (
     anthropic_chat_completions_request,
 )
 from letta.llm_api.aws_bedrock import has_valid_aws_credentials
-from letta.llm_api.azure_openai import azure_openai_chat_completions_request
 from letta.llm_api.deepseek import build_deepseek_chat_completions_request, convert_deepseek_response_to_chatcompletion
 from letta.llm_api.helpers import add_inner_thoughts_to_functions, unpack_all_inner_thoughts_from_kwargs
 from letta.llm_api.openai import (
@@ -312,44 +311,6 @@ def create(
 
         return response
 
-    # azure
-    elif llm_config.model_endpoint_type == "azure":
-        if stream:
-            raise NotImplementedError(f"Streaming not yet implemented for {llm_config.model_endpoint_type}")
-
-        if model_settings.azure_api_key is None:
-            raise LettaConfigurationError(
-                message="Azure API key is missing. Did you set AZURE_API_KEY in your env?", missing_fields=["azure_api_key"]
-            )
-
-        if model_settings.azure_base_url is None:
-            raise LettaConfigurationError(
-                message="Azure base url is missing. Did you set AZURE_BASE_URL in your env?", missing_fields=["azure_base_url"]
-            )
-
-        if model_settings.azure_api_version is None:
-            raise LettaConfigurationError(
-                message="Azure API version is missing. Did you set AZURE_API_VERSION in your env?", missing_fields=["azure_api_version"]
-            )
-
-        # Set the llm config model_endpoint from model_settings
-        # For Azure, this model_endpoint is required to be configured via env variable, so users don't need to provide it in the LLM config
-        llm_config.model_endpoint = model_settings.azure_base_url
-        chat_completion_request = build_openai_chat_completions_request(
-            llm_config, messages, user_id, functions, function_call, use_tool_naming
-        )
-
-        response = azure_openai_chat_completions_request(
-            model_settings=model_settings,
-            llm_config=llm_config,
-            chat_completion_request=chat_completion_request,
-        )
-
-        if llm_config.put_inner_thoughts_in_kwargs:
-            response = unpack_all_inner_thoughts_from_kwargs(response=response, inner_thoughts_key=INNER_THOUGHTS_KWARG)
-
-        return response
-
     elif llm_config.model_endpoint_type == "anthropic":
         if not use_tool_naming:
             raise NotImplementedError("Only tool calling supported on Anthropic API requests")