diff --git a/build/lib/litellm/__init__.py b/build/lib/litellm/__init__.py
index 22e8bfa87..e3d4a8d84 100644
--- a/build/lib/litellm/__init__.py
+++ b/build/lib/litellm/__init__.py
@@ -2,6 +2,10 @@ success_callback = []
 failure_callback = []
 set_verbose=False
 telemetry=True
+
+####### PROXY PARAMS ################### configurable params if you use proxy models like Helicone
+api_base = None
+headers = None
 ####### COMPLETION MODELS ###################
 open_ai_chat_completion_models = [
   'gpt-3.5-turbo', 
diff --git a/build/lib/litellm/main.py b/build/lib/litellm/main.py
index 55d560814..16faba2bd 100644
--- a/build/lib/litellm/main.py
+++ b/build/lib/litellm/main.py
@@ -75,43 +75,66 @@ def completion(
     if azure == True:
       # azure configs
       openai.api_type = "azure"
-      openai.api_base = os.environ.get("AZURE_API_BASE")
+      openai.api_base = litellm.api_base if litellm.api_base is not None else os.environ.get("AZURE_API_BASE")
       openai.api_version = os.environ.get("AZURE_API_VERSION")
       openai.api_key = api_key if api_key is not None else os.environ.get("AZURE_API_KEY")
       ## LOGGING
       logging(model=model, input=messages, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.ChatCompletion.create(
-        engine=model,
-        messages = messages,
-        **optional_params
-      )
+      if litellm.headers:
+         response = openai.ChatCompletion.create(
+            engine=model,
+            messages = messages,
+            headers = litellm.headers,
+            **optional_params,
+          )
+      else:
+        response = openai.ChatCompletion.create(
+          engine=model,
+          messages = messages,
+          **optional_params
+        )
     elif model in litellm.open_ai_chat_completion_models:
       openai.api_type = "openai"
-      openai.api_base = "https://api.openai.com/v1"
+      openai.api_base = litellm.api_base if litellm.api_base is not None else "https://api.openai.com/v1"
       openai.api_version = None
       openai.api_key = api_key if api_key is not None else os.environ.get("OPENAI_API_KEY")
       ## LOGGING
       logging(model=model, input=messages, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.ChatCompletion.create(
-        model=model,
-        messages = messages,
-        **optional_params
-      )
+      if litellm.headers:
+         response = openai.ChatCompletion.create(
+          model=model,
+          messages = messages,
+          headers = litellm.headers,
+          **optional_params
+        )
+      else:
+        response = openai.ChatCompletion.create(
+          model=model,
+          messages = messages,
+          **optional_params
+        )
     elif model in litellm.open_ai_text_completion_models:
       openai.api_type = "openai"
-      openai.api_base = "https://api.openai.com/v1"
+      openai.api_base = litellm.api_base if litellm.api_base is not None else "https://api.openai.com/v1"
       openai.api_version = None
       openai.api_key = api_key if api_key is not None else os.environ.get("OPENAI_API_KEY")
       prompt = " ".join([message["content"] for message in messages])
       ## LOGGING
       logging(model=model, input=prompt, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.Completion.create(
+      if litellm.headers:
+        response = openai.Completion.create(
           model=model,
-          prompt = prompt
-      )
+          prompt = prompt,
+          headers = litellm.headers,
+        )
+      else:
+        response = openai.Completion.create(
+            model=model,
+            prompt = prompt
+        )
     elif "replicate" in model:
       # replicate defaults to os.environ.get("REPLICATE_API_TOKEN")
       # checking in case user set it to REPLICATE_API_KEY instead 
@@ -171,10 +194,10 @@ def completion(
       logging(model=model, input=prompt, azure=azure, additional_args={"max_tokens": max_tokens}, logger_fn=logger_fn)
       ## COMPLETION CALL
       completion = anthropic.completions.create(
-          model=model,
-          prompt=prompt,
-          max_tokens_to_sample=max_tokens_to_sample
-      )
+            model=model,
+            prompt=prompt,
+            max_tokens_to_sample=max_tokens_to_sample
+        )
       new_response = {
         "choices": [
           {
diff --git a/dist/litellm-0.1.219-py3-none-any.whl b/dist/litellm-0.1.219-py3-none-any.whl
deleted file mode 100644
index 439f6b47a..000000000
Binary files a/dist/litellm-0.1.219-py3-none-any.whl and /dev/null differ
diff --git a/dist/litellm-0.1.219.tar.gz b/dist/litellm-0.1.219.tar.gz
deleted file mode 100644
index 116eed418..000000000
Binary files a/dist/litellm-0.1.219.tar.gz and /dev/null differ
diff --git a/dist/litellm-0.1.220-py3-none-any.whl b/dist/litellm-0.1.220-py3-none-any.whl
new file mode 100644
index 000000000..d12f0568c
Binary files /dev/null and b/dist/litellm-0.1.220-py3-none-any.whl differ
diff --git a/dist/litellm-0.1.220.tar.gz b/dist/litellm-0.1.220.tar.gz
new file mode 100644
index 000000000..63d50fdac
Binary files /dev/null and b/dist/litellm-0.1.220.tar.gz differ
diff --git a/litellm.egg-info/PKG-INFO b/litellm.egg-info/PKG-INFO
index f6f15a462..2e24f886b 100644
--- a/litellm.egg-info/PKG-INFO
+++ b/litellm.egg-info/PKG-INFO
@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: litellm
-Version: 0.1.219
+Version: 0.1.220
 Summary: Library to easily interface with LLM API providers
 Author: BerriAI
 License-File: LICENSE
diff --git a/litellm/__init__.py b/litellm/__init__.py
index 22e8bfa87..e3d4a8d84 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -2,6 +2,10 @@ success_callback = []
 failure_callback = []
 set_verbose=False
 telemetry=True
+
+####### PROXY PARAMS ################### configurable params if you use proxy models like Helicone
+api_base = None
+headers = None
 ####### COMPLETION MODELS ###################
 open_ai_chat_completion_models = [
   'gpt-3.5-turbo', 
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
new file mode 100644
index 000000000..19b37aa2f
Binary files /dev/null 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
new file mode 100644
index 000000000..7b8de5bd0
Binary files /dev/null and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/timeout.cpython-311.pyc b/litellm/__pycache__/timeout.cpython-311.pyc
new file mode 100644
index 000000000..880e08abb
Binary files /dev/null and b/litellm/__pycache__/timeout.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
new file mode 100644
index 000000000..61ebdb129
Binary files /dev/null and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/main.py b/litellm/main.py
index 55d560814..16faba2bd 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -75,43 +75,66 @@ def completion(
     if azure == True:
       # azure configs
       openai.api_type = "azure"
-      openai.api_base = os.environ.get("AZURE_API_BASE")
+      openai.api_base = litellm.api_base if litellm.api_base is not None else os.environ.get("AZURE_API_BASE")
       openai.api_version = os.environ.get("AZURE_API_VERSION")
       openai.api_key = api_key if api_key is not None else os.environ.get("AZURE_API_KEY")
       ## LOGGING
       logging(model=model, input=messages, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.ChatCompletion.create(
-        engine=model,
-        messages = messages,
-        **optional_params
-      )
+      if litellm.headers:
+         response = openai.ChatCompletion.create(
+            engine=model,
+            messages = messages,
+            headers = litellm.headers,
+            **optional_params,
+          )
+      else:
+        response = openai.ChatCompletion.create(
+          engine=model,
+          messages = messages,
+          **optional_params
+        )
     elif model in litellm.open_ai_chat_completion_models:
       openai.api_type = "openai"
-      openai.api_base = "https://api.openai.com/v1"
+      openai.api_base = litellm.api_base if litellm.api_base is not None else "https://api.openai.com/v1"
       openai.api_version = None
       openai.api_key = api_key if api_key is not None else os.environ.get("OPENAI_API_KEY")
       ## LOGGING
       logging(model=model, input=messages, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.ChatCompletion.create(
-        model=model,
-        messages = messages,
-        **optional_params
-      )
+      if litellm.headers:
+         response = openai.ChatCompletion.create(
+          model=model,
+          messages = messages,
+          headers = litellm.headers,
+          **optional_params
+        )
+      else:
+        response = openai.ChatCompletion.create(
+          model=model,
+          messages = messages,
+          **optional_params
+        )
     elif model in litellm.open_ai_text_completion_models:
       openai.api_type = "openai"
-      openai.api_base = "https://api.openai.com/v1"
+      openai.api_base = litellm.api_base if litellm.api_base is not None else "https://api.openai.com/v1"
       openai.api_version = None
       openai.api_key = api_key if api_key is not None else os.environ.get("OPENAI_API_KEY")
       prompt = " ".join([message["content"] for message in messages])
       ## LOGGING
       logging(model=model, input=prompt, azure=azure, logger_fn=logger_fn)
       ## COMPLETION CALL
-      response = openai.Completion.create(
+      if litellm.headers:
+        response = openai.Completion.create(
           model=model,
-          prompt = prompt
-      )
+          prompt = prompt,
+          headers = litellm.headers,
+        )
+      else:
+        response = openai.Completion.create(
+            model=model,
+            prompt = prompt
+        )
     elif "replicate" in model:
       # replicate defaults to os.environ.get("REPLICATE_API_TOKEN")
       # checking in case user set it to REPLICATE_API_KEY instead 
@@ -171,10 +194,10 @@ def completion(
       logging(model=model, input=prompt, azure=azure, additional_args={"max_tokens": max_tokens}, logger_fn=logger_fn)
       ## COMPLETION CALL
       completion = anthropic.completions.create(
-          model=model,
-          prompt=prompt,
-          max_tokens_to_sample=max_tokens_to_sample
-      )
+            model=model,
+            prompt=prompt,
+            max_tokens_to_sample=max_tokens_to_sample
+        )
       new_response = {
         "choices": [
           {
diff --git a/litellm/tests/test_proxy_api.py b/litellm/tests/test_proxy_api.py
new file mode 100644
index 000000000..348e83e88
--- /dev/null
+++ b/litellm/tests/test_proxy_api.py
@@ -0,0 +1,15 @@
+import sys, os
+import traceback
+sys.path.insert(0, os.path.abspath('../..'))  # Adds the parent directory to the system path
+import litellm
+from litellm import embedding, completion
+
+litellm.api_base = "https://oai.hconeai.com/v1"
+litellm.headers = {"Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}"}
+
+response = litellm.completion(
+    model="gpt-3.5-turbo",
+    messages=[{"role": "user", "content": "how does a court case get to the Supreme Court?"}]
+)
+
+print(response)
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 524f7ba0c..a33431fb0 100644
--- a/setup.py
+++ b/setup.py
@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='litellm',
-    version='0.1.219',
+    version='0.1.220',
     description='Library to easily interface with LLM API providers',
     author='BerriAI',
     packages=[