diff --git a/litellm/__init__.py b/litellm/__init__.py
index 5f526e0eb..ca6830293 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -48,6 +48,7 @@ api_base = None
 headers = None
 api_version = None
 organization = None
+config_path = None
 ####### Secret Manager #####################
 secret_manager_client = None
 ####### COMPLETION MODELS ###################
diff --git a/litellm/config.json b/litellm/config.json
new file mode 100644
index 000000000..a6707a1ee
--- /dev/null
+++ b/litellm/config.json
@@ -0,0 +1,6 @@
+{
+    "model": "command-nightly",
+    "temperature": 0.7,
+    "max_tokens": 10
+  }
+  
\ No newline at end of file
diff --git a/litellm/main.py b/litellm/main.py
index e5291a9b7..3a93f9c24 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -8,7 +8,7 @@ from litellm import client, logging, exception_type, timeout, get_optional_param
 import tiktoken
 from concurrent.futures import ThreadPoolExecutor
 encoding = tiktoken.get_encoding("cl100k_base")
-from litellm.utils import get_secret, install_and_import, CustomStreamWrapper
+from litellm.utils import get_secret, install_and_import, CustomStreamWrapper, read_config_args
 ####### ENVIRONMENT VARIABLES ###################
 dotenv.load_dotenv() # Loading env variables using dotenv
 new_response = {
@@ -38,7 +38,7 @@ async def acompletion(*args, **kwargs):
 # @retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(2), reraise=True, retry_error_callback=lambda retry_state: setattr(retry_state.outcome, 'retry_variable', litellm.retry)) # retry call, turn this off by setting `litellm.retry = False`
 @timeout(60) ## set timeouts, in case calls hang (e.g. Azure) - default is 60s, override with `force_timeout`
 def completion(
-    model, messages, # required params
+    messages, model="gpt-3.5-turbo",# required params
     # Optional OpenAI params: see https://platform.openai.com/docs/api-reference/chat/create
     functions=[], function_call="", # optional params
     temperature=1, top_p=1, n=1, stream=False, stop=None, max_tokens=float('inf'),
@@ -504,3 +504,10 @@ def print_verbose(print_statement):
     if random.random() <= 0.3:
       print("Get help - https://discord.com/invite/wuPM9dRgDw")
 
+def config_completion(**kwargs):
+  if litellm.config_path != None:
+    config_args = read_config_args(litellm.config_path)
+    # overwrite any args passed in with config args
+    return completion(**kwargs, **config_args)
+  else:
+    raise ValueError("No config path set, please set a config path using `litellm.config_path = 'path/to/config.json'`")
\ No newline at end of file
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 9583ea03f..54c1a2ab1 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -217,4 +217,19 @@ def test_completion_together_ai_stream():
         for chunk in response:
             print(chunk['choices'][0]['delta']) # same as openai format
     except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
\ No newline at end of file
+        pytest.fail(f"Error occurred: {e}")
+
+# test config file with completion # 
+def test_completion_openai_config():
+    try:
+        litellm.config_path = "../config.json"
+        litellm.set_verbose = True
+        response = litellm.config_completion(messages=messages)
+        # Add any assertions here to check the response
+        print(response)
+        litellm.config_path = None
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
+
diff --git a/litellm/utils.py b/litellm/utils.py
index e8f5f3976..4fa2751a6 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -709,3 +709,19 @@ class CustomStreamWrapper:
           completion_obj["content"] = chunk.text
         # return this for all models
         return {"choices": [{"delta": completion_obj}]}
+
+
+
+########## Reading Config File ############################
+def read_config_args(config_path):
+    try:
+        import os
+        current_path = os.getcwd()
+        with open(config_path, "r") as config_file:
+            config = json.load(config_file)
+
+        # read keys/ values from config file and return them
+        return config
+    except Exception as e:
+        print("An error occurred while reading config:", str(e))
+        raise e
\ No newline at end of file