diff --git a/README.md b/README.md
index c3ea724..b75596e 100644
--- a/README.md
+++ b/README.md
@@ -52,7 +52,7 @@ After you have Python and PostgreSQL installed, follow these steps:
 5. `pip install -r requirements.txt` (install the dependencies)
 6. `cd pilot`
 7. `mv .env.example .env` (create the .env file)
-8. Add your OpenAI API key and the PostgreSQL database info to the `.env` file
+8. Add your environment (OpenAI/Azure), your API key and the PostgreSQL database info to the `.env` file
 9. `python db_init.py` (initialize the database)
 10. `python main.py` (start GPT Pilot)
 
diff --git a/pilot/.env.example b/pilot/.env.example
index d53210e..e7b661c 100644
--- a/pilot/.env.example
+++ b/pilot/.env.example
@@ -1,4 +1,11 @@
+#OPENAI or AZURE
+ENDPOINT=OPENAI
 OPENAI_API_KEY=
+AZURE_API_KEY=
+AZURE_ENDPOINT=
+#In case of Azure endpoint, change this to your deployed model name
+MODEL_NAME=gpt-4
+MAX_TOKENS=8192
 DB_NAME=gpt-pilot
 DB_HOST=localhost
 DB_PORT=5432
diff --git a/pilot/const/llm.py b/pilot/const/llm.py
index ca42267..8ae8ab8 100644
--- a/pilot/const/llm.py
+++ b/pilot/const/llm.py
@@ -1,4 +1,5 @@
+import os
+MAX_GPT_MODEL_TOKENS = int(os.getenv('MAX_TOKENS'))
 MIN_TOKENS_FOR_GPT_RESPONSE = 600
-MAX_GPT_MODEL_TOKENS = 8192
 MAX_QUESTIONS = 5
-END_RESPONSE = "EVERYTHING_CLEAR"
+END_RESPONSE = "EVERYTHING_CLEAR"
\ No newline at end of file
diff --git a/pilot/utils/llm_connection.py b/pilot/utils/llm_connection.py
index 58f4b6a..369af7c 100644
--- a/pilot/utils/llm_connection.py
+++ b/pilot/utils/llm_connection.py
@@ -46,8 +46,11 @@ def get_tokens_in_messages(messages: List[str]) -> int:
     tokenized_messages = [tokenizer.encode(message['content']) for message in messages]
     return sum(len(tokens) for tokens in tokenized_messages)
 
+#get endpoint and model name from .ENV file
+model = os.getenv('MODEL_NAME')
+endpoint = os.getenv('ENDPOINT')
 
-def num_tokens_from_functions(functions, model="gpt-4"):
+def num_tokens_from_functions(functions, model=model):
     """Return the number of tokens used by a list of functions."""
     encoding = tiktoken.get_encoding("cl100k_base")
 
@@ -171,13 +174,22 @@ def stream_gpt_completion(data, req_type):
 
     # spinner = spinner_start(colored("Waiting for OpenAI API response...", 'yellow'))
     # print(colored("Stream response from OpenAI:", 'yellow'))
-    api_key = os.getenv("OPENAI_API_KEY")
 
     logger.info(f'Request data: {data}')
 
+    # Check if the ENDPOINT is AZURE
+    if endpoint == 'AZURE':
+        # If yes, get the AZURE_ENDPOINT from .ENV file
+        endpoint_url = os.getenv('AZURE_ENDPOINT') + '/openai/deployments/' + model + '/chat/completions?api-version=2023-05-15'
+        headers = {'Content-Type': 'application/json', 'api-key':  os.getenv('AZURE_API_KEY')}
+    else:
+        # If not, send the request to the OpenAI endpoint
+        headers = {'Content-Type': 'application/json', 'Authorization':  'Bearer ' + os.getenv("OPENAI_API_KEY")}
+        endpoint_url = 'https://api.openai.com/v1/chat/completions'
+
     response = requests.post(
-        'https://api.openai.com/v1/chat/completions',
-        headers={'Content-Type': 'application/json', 'Authorization': 'Bearer ' + api_key},
+        endpoint_url,
+        headers=headers,
         json=data,
         stream=True
     )