diff --git a/litellm/llms/huggingface_restapi.py b/litellm/llms/huggingface_restapi.py
index 8d652cf671..c885040a58 100644
--- a/litellm/llms/huggingface_restapi.py
+++ b/litellm/llms/huggingface_restapi.py
@@ -48,6 +48,8 @@ class HuggingfaceRestAPILLM:
         completion_url: str = ""
         if "https" in model:
             completion_url = model
+        elif custom_api_base:
+            completion_url = custom_api_base
         elif "HF_API_BASE" in os.environ:
             completion_url = os.getenv("HF_API_BASE", "")
         else:
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 31531678ca..d890c54153 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -83,16 +83,16 @@ def test_completion_claude_stream():
 #         pytest.fail(f"Error occurred: {e}")
 
 
-def test_completion_hf_deployed_api():
-    try:
-        user_message = "There's a llama in my garden 😱 What should I do?"
-        messages = [{ "content": user_message,"role": "user"}]
-        response = completion(model="huggingface/https://ji16r2iys9a8rjk2.us-east-1.aws.endpoints.huggingface.cloud", messages=messages, logger_fn=logger_fn)
-        # Add any assertions here to check the response
-        print(response)
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
-test_completion_hf_deployed_api()
+# def test_completion_hf_deployed_api():
+#     try:
+#         user_message = "There's a llama in my garden 😱 What should I do?"
+#         messages = [{ "content": user_message,"role": "user"}]
+#         response = completion(model="huggingface/https://ji16r2iys9a8rjk2.us-east-1.aws.endpoints.huggingface.cloud", messages=messages, logger_fn=logger_fn)
+#         # Add any assertions here to check the response
+#         print(response)
+#     except Exception as e:
+#         pytest.fail(f"Error occurred: {e}")
+
 
 # def test_completion_cohere(): # commenting for now as the cohere endpoint is being flaky
 #     try: