diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index c3db66499a..fe98e178db 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -594,6 +594,9 @@ def test_completion_azure():
         # )
         # Add any assertions here to check the response
         print(response)
+
+        cost = completion_cost(completion_response=response)
+        print("Cost for azure completion request", cost)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
diff --git a/litellm/utils.py b/litellm/utils.py
index e9e649252a..8ca70fa64a 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1612,7 +1612,7 @@ def cost_per_token(model="gpt-3.5-turbo", prompt_tokens=0, completion_tokens=0):
         )
         return prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar
     else:
-        # calculate average input cost
+        # calculate average input cost, azure/gpt-deployments can potentially go here if users don't specify, gpt-4, gpt-3.5-turbo. LLMs litellm knows
         input_cost_sum = 0
         output_cost_sum = 0
         model_cost_ref = litellm.model_cost