diff --git a/litellm/__init__.py b/litellm/__init__.py
index d47c8e7b873..f81a9093a6e 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -15,7 +15,7 @@ openrouter_key = None
 huggingface_key = None
 vertex_project = None
 vertex_location = None
-
+caching = False
 hugging_api_token = None
 model_cost = {
     "gpt-3.5-turbo": {"max_tokens": 4000, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002},
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 07167d14986..f76206ecdc8 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 d2da312cb36..f0af40629ad 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 c8658d0785a..fe9983c5b45 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/tests/test_caching.py b/litellm/tests/test_caching.py
new file mode 100644
index 00000000000..895e9e0fac4
--- /dev/null
+++ b/litellm/tests/test_caching.py
@@ -0,0 +1,27 @@
+import sys, os
+import traceback
+from dotenv import load_dotenv
+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
+
+litellm.caching = True
+messages = [{"role": "user", "content": "Hey, how's it going?"}]
+
+
+
+# test if response cached
+try:
+    response1 = completion(model="gpt-3.5-turbo", messages=messages)
+    response2 = completion(model="gpt-3.5-turbo", messages=messages)
+    if response2 != response1:
+        print(f"response1: {response1}")
+        print(f"response2: {response2}")
+        raise Exception
+except Exception as e:
+    print(f"error occurred: {traceback.format_exc()}") 
+    pytest.fail(f"Error occurred: {e}")
+
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 5bd78b33f70..8c094613140 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -213,7 +213,7 @@ def test_completion_together_ai_stream():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-
+test_completion_together_ai_stream()
 def test_petals():
     model_name = "stabilityai/StableBeluga2"
     try:
diff --git a/litellm/utils.py b/litellm/utils.py
index 545138313b1..6d828b26a9a 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -28,6 +28,7 @@ supabaseClient = None
 callback_list = []
 user_logger_fn = None
 additional_details = {}
+local_cache = {}
 
 def print_verbose(print_statement):
   if litellm.set_verbose:
@@ -138,12 +139,22 @@ def client(original_function):
 
     def wrapper(*args, **kwargs):
         start_time = None
+        result = None
         try:
           function_setup(*args, **kwargs)
           ## MODEL CALL
           start_time = datetime.datetime.now()
-          result = original_function(*args, **kwargs)
+          ## CHECK CACHE RESPONSES 
+          messages = args[1] if len(args) > 1 else kwargs["messages"]
+          prompt = " ".join(message["content"] for message in messages) 
+          if litellm.caching and prompt in local_cache:
+            result = local_cache[prompt]
+          else:
+            result = original_function(*args, **kwargs)
           end_time = datetime.datetime.now()
+          ## CACHE RESPONSES 
+          if litellm.caching:
+            local_cache[prompt] = result
           ## LOG SUCCESS 
           crash_reporting(*args, **kwargs)
           my_thread = threading.Thread(target=handle_success, args=(args, kwargs, result, start_time, end_time)) # don't interrupt execution of main thread