diff --git a/litellm/__init__.py b/litellm/__init__.py
index 6b824067818..aa5c547bdd1 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -140,7 +140,8 @@ open_ai_embedding_models = [
 ]
 
 from .timeout import timeout
-from .utils import client, logging, exception_type, get_optional_params, modify_integration, token_counter, cost_per_token, completion_cost, load_test_model, get_litellm_params
+from .testing import *
+from .utils import client, logging, exception_type, get_optional_params, modify_integration, token_counter, cost_per_token, completion_cost, get_litellm_params
 from .main import *  # Import all the symbols from main.py
 from .integrations import *
 from openai.error import AuthenticationError, InvalidRequestError, RateLimitError, ServiceUnavailableError, OpenAIError
\ No newline at end of file
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 3a9b2741d5d..07167d14986 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index afc8469fd96..d2da312cb36 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 92c3af615df..c8658d0785a 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/testing.py b/litellm/testing.py
new file mode 100644
index 00000000000..9b13f1f714d
--- /dev/null
+++ b/litellm/testing.py
@@ -0,0 +1,57 @@
+import litellm
+import time 
+from concurrent.futures import ThreadPoolExecutor
+
+def batch_completion(*args, **kwargs):
+  batch_messages = args[1] if len(args) > 1 else kwargs.get("messages")
+  results = []
+  completions = []
+  exceptions = []
+  times = []
+  with ThreadPoolExecutor() as executor:
+    for message_list in batch_messages:
+      if len(args) > 1:
+        args_modified = list(args)
+        args_modified[1] = message_list
+        future = executor.submit(litellm.completion, *args_modified)
+      else:
+        kwargs_modified = dict(kwargs)
+        kwargs_modified["messages"] = message_list
+        future = executor.submit(litellm.completion, *args, **kwargs_modified)
+      completions.append(future)
+  
+  # Retrieve the results and calculate elapsed time for each completion call
+  for future in completions:
+    start_time = time.time()
+    try:
+      result = future.result()
+      end_time = time.time()
+      elapsed_time = end_time - start_time
+      result_dict = {"status": "succeeded", "response": future.result(), "response_time": elapsed_time}
+      results.append(result_dict)
+    except Exception as e:
+      end_time = time.time()
+      elapsed_time = end_time - start_time
+      result_dict = {"status": "succeeded", "response": e, "response_time": elapsed_time}
+      results.append(result_dict)
+  
+  return results
+
+def load_test_model(model: str, custom_llm_provider: str = None, custom_api_base: str = None, prompt: str = None, num_calls: int = None, force_timeout: int = None):
+  test_prompt = "Hey, how's it going"
+  test_calls = 100
+  if prompt:
+     test_prompt = prompt
+  if num_calls:
+     test_calls = num_calls
+  messages = [[{"role": "user", "content": test_prompt}] for _ in range(test_calls)]
+  start_time = time.time()
+  try:
+    results = batch_completion(model=model, messages=messages, custom_llm_provider=custom_llm_provider, custom_api_base = custom_api_base, force_timeout=force_timeout)
+    end_time = time.time() 
+    response_time = end_time - start_time
+    return {"total_response_time": response_time, "calls_made": test_calls, "prompt": test_prompt, "results": results}
+  except Exception as e:
+    end_time = time.time() 
+    response_time = end_time - start_time
+    return {"total_response_time": response_time, "calls_made": test_calls, "prompt": test_prompt, "exception": e}
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
index 6d676f2a94a..9edb2a2abbe 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.400"
+version = "0.1.401"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"