diff --git a/litellm/tests/test_completion_cost.py b/litellm/tests/test_completion_cost.py
index 3828ef7997..d759484a6b 100644
--- a/litellm/tests/test_completion_cost.py
+++ b/litellm/tests/test_completion_cost.py
@@ -1,22 +1,38 @@
 
-# import sys, os
-# import traceback
-# from dotenv import load_dotenv
+import sys, os
+import traceback
+from dotenv import load_dotenv
 
-# load_dotenv()
-# import os
+load_dotenv()
+import os
 
-# sys.path.insert(
-#     0, os.path.abspath("../..")
-# )  # Adds the parent directory to the system path
-# import pytest
-# import litellm
-# from litellm import embedding, completion, text_completion
-# from litellm.utils import completion_cost
+sys.path.insert(
+    0, os.path.abspath("../..")
+)  # Adds the parent directory to the system path
+import pytest
+import litellm
+from litellm import embedding, completion, text_completion
+from litellm.utils import completion_cost
 
 
-# print(completion_cost(
-#         model="togethercomputer/llama-2-2b-chat", 
-#         prompt="gm", 
-#         completion="hello"
-#     ))
\ No newline at end of file
+user_message = "Write a short poem about the sky"
+messages = [{"content": user_message, "role": "user"}]
+
+
+def test_completion_togetherai_cost():
+    try:
+        response = completion(
+            model="together_ai/togethercomputer/llama-2-70b-chat",
+            messages=messages,
+            request_timeout=200,
+        )
+        # Add any assertions here to check the response
+        print(response)
+        print("Completion Cost:")
+        cost = completion_cost(completion_response=response)
+        formatted_string = f"${float(cost):.10f}"
+        print(formatted_string)
+        
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+# test_completion_togetherai_cost()
\ No newline at end of file
diff --git a/litellm/utils.py b/litellm/utils.py
index 782d0ac4a9..48e61b184c 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -563,7 +563,6 @@ def client(original_function):
                 ):  # make it easy to get to the debugger logs if you've initialized it
                     e.message += f"\n Check the log in your dashboard - {liteDebuggerClient.dashboard_url}"
             raise e
-
     return wrapper
 
 
@@ -571,7 +570,7 @@ def client(original_function):
 
 
 # Extract the number of billion parameters from the model name
-# together_compute
+# only used for together_computer LLMs
 def get_model_params_and_category(model_name):
     import re
     params_match = re.search(r'(\d+b)', model_name) # catch all decimals like 3b, 70b, etc    
@@ -647,15 +646,23 @@ def cost_per_token(model="gpt-3.5-turbo", prompt_tokens=0, completion_tokens=0):
 def completion_cost(
         model="gpt-3.5-turbo", 
         prompt="", 
-        completion=""
+        completion="",
+        completion_response=None
     ):
-    prompt_tokens = token_counter(model=model, text=prompt)
-    completion_tokens = token_counter(model=model, text=completion)
+    prompt_tokens = 0
+    completion_tokens = 0
+    if completion_response != None:
+        # get input/output tokens from completion_response
+        prompt_tokens = completion_response['usage']['prompt_tokens']
+        completion_tokens = completion_response['usage']['completion_tokens']
+        model = completion_response['model'] # get model from completion_response
+    else:
+        prompt_tokens = token_counter(model=model, text=prompt)
+        completion_tokens = token_counter(model=model, text=completion)
     if "togethercomputer" in model:
         # together ai prices based on size of llm
         # get_model_params_and_category takes a model name and returns the category of LLM size it is in model_prices_and_context_window.json 
         model = get_model_params_and_category(model)
-        # print(together_catgeory)
     prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar = cost_per_token(
         model=model, prompt_tokens=prompt_tokens, completion_tokens=completion_tokens
     )