diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index adb45149c9..a9e7a21749 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/main.py b/litellm/main.py
index 6042a5eaa1..73d8c7c472 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -118,6 +118,8 @@ def completion(
         model_response = ModelResponse()
         if azure:  # this flag is deprecated, remove once notebooks are also updated.
             custom_llm_provider = "azure"
+            if deployment_id:
+                model=deployment_id
         elif (
             model.split("/", 1)[0] in litellm.provider_list
         ):  # allow custom provider to be passed in via the model name "azure/chatgpt-test"
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index caabe467e2..ae59af2044 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -337,6 +337,19 @@ def test_completion_azure():
         pytest.fail(f"Error occurred: {e}")
 
 
+def test_completion_azure_deployment_id():
+    try:
+        response = completion(
+            model="chatgpt-3.5-turbo",
+            deployment_id="chatgpt-v-2",
+            messages=messages,
+            azure=True,
+        )
+        # Add any assertions here to check the response
+        print(response)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
 # Replicate API endpoints are unstable -> throw random CUDA errors -> this means our tests can fail even if our tests weren't incorrect.
 def test_completion_replicate_llama_stream():
     model_name = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
@@ -410,8 +423,6 @@ def test_customprompt_together_ai():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-test_customprompt_together_ai()
-
 def test_completion_sagemaker():
     try:
         response = completion(