diff --git a/litellm/llms/azure.py b/litellm/llms/azure.py
index 01b54987b2d..0f678690277 100644
--- a/litellm/llms/azure.py
+++ b/litellm/llms/azure.py
@@ -270,6 +270,14 @@ class AzureChatCompletion(BaseLLM):
                     azure_client = AzureOpenAI(**azure_client_params)
                 else:
                     azure_client = client
+                    if api_version is not None and isinstance(
+                        azure_client._custom_query, dict
+                    ):
+                        # set api_version to version passed by user
+                        azure_client._custom_query.setdefault(
+                            "api-version", api_version
+                        )
+
                 response = azure_client.chat.completions.create(**data, timeout=timeout)  # type: ignore
                 stringified_response = response.model_dump()
                 ## LOGGING
@@ -333,10 +341,17 @@ class AzureChatCompletion(BaseLLM):
                 azure_client_params["api_key"] = api_key
             elif azure_ad_token is not None:
                 azure_client_params["azure_ad_token"] = azure_ad_token
+
+            # setting Azure client
             if client is None:
                 azure_client = AsyncAzureOpenAI(**azure_client_params)
             else:
                 azure_client = client
+                if api_version is not None and isinstance(
+                    azure_client._custom_query, dict
+                ):
+                    # set api_version to version passed by user
+                    azure_client._custom_query.setdefault("api-version", api_version)
             ## LOGGING
             logging_obj.pre_call(
                 input=data["messages"],
@@ -401,6 +416,9 @@ class AzureChatCompletion(BaseLLM):
             azure_client = AzureOpenAI(**azure_client_params)
         else:
             azure_client = client
+            if api_version is not None and isinstance(azure_client._custom_query, dict):
+                # set api_version to version passed by user
+                azure_client._custom_query.setdefault("api-version", api_version)
         ## LOGGING
         logging_obj.pre_call(
             input=data["messages"],
@@ -454,6 +472,11 @@ class AzureChatCompletion(BaseLLM):
                 azure_client = AsyncAzureOpenAI(**azure_client_params)
             else:
                 azure_client = client
+                if api_version is not None and isinstance(
+                    azure_client._custom_query, dict
+                ):
+                    # set api_version to version passed by user
+                    azure_client._custom_query.setdefault("api-version", api_version)
             ## LOGGING
             logging_obj.pre_call(
                 input=data["messages"],
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 19ac5c96118..d9642b81037 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -2670,6 +2670,11 @@ async def chat_completion(
         except:
             data = json.loads(body_str)
 
+        # Azure OpenAI only: check if user passed api-version
+        query_params = dict(request.query_params)
+        if "api-version" in query_params:
+            data["api_version"] = query_params["api-version"]
+
         # Include original request and headers in the data
         data["proxy_server_request"] = {
             "url": str(request.url),