diff --git a/src/llm/openai/chatgpt4turbo_preview/Dockerfile b/src/llm/openai/chatgpt4turbo_preview/Dockerfile
new file mode 100644
index 0000000..7cebb27
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/Dockerfile
@@ -0,0 +1,15 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+WORKDIR /app
+
+#install requirements
+COPY requirements.txt requirements.txt
+RUN pip3 install -r requirements.txt
+
+# Copy the rest of the application code to the working directory
+COPY . /app/
+EXPOSE 8000
+# Set the entrypoint for the container
+CMD ["hypercorn", "--bind", "0.0.0.0:8000", "api:app"]
+
diff --git a/src/llm/openai/chatgpt4turbo_preview/__init__.py b/src/llm/openai/chatgpt4turbo_preview/__init__.py
new file mode 100644
index 0000000..55963ef
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/__init__.py
@@ -0,0 +1,2 @@
+from .request import ModelRequest
+from .request import Model
\ No newline at end of file
diff --git a/src/llm/openai/chatgpt4turbo_preview/api.py b/src/llm/openai/chatgpt4turbo_preview/api.py
new file mode 100644
index 0000000..12f4a8b
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/api.py
@@ -0,0 +1,20 @@
+from model import Model
+from request import ModelRequest
+from quart import Quart, request
+import aiohttp
+
+#from fastapi import FastAPI, Body
+app = Quart(__name__)
+#app.client = aiohttp.ClientSession()
+#app = FastAPI()
+
+@app.before_serving
+async def startup():
+    app.client = aiohttp.ClientSession()
+
+@app.route('/', methods=['POST'])
+async def answer():
+    data = await request.get_json()
+    req = ModelRequest(**data)
+    model = Model(app)
+    return await model.inference(req)
diff --git a/src/llm/openai/chatgpt4turbo_preview/model.py b/src/llm/openai/chatgpt4turbo_preview/model.py
new file mode 100644
index 0000000..8ac0f7b
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/model.py
@@ -0,0 +1,28 @@
+import os
+import openai
+import openai_async
+from cache import AsyncTTL
+from request import ModelRequest
+from tenacity import retry, wait_random_exponential, stop_after_attempt
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+class Model:
+    def __new__(cls, context):
+        cls.context = context
+        if not hasattr(cls, 'instance'):
+            cls.instance = super(Model, cls).__new__(cls)
+        return cls.instance
+
+    @retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
+    async def inference(self, request: ModelRequest):
+        response = await openai_async.chat_complete(
+            openai.api_key,
+            timeout=20000,
+            payload={
+                "model": "gpt-4-1106-preview",
+                "temperature": 0,
+                "messages": request.prompt,
+            },
+        )
+        return response.json()
diff --git a/src/llm/openai/chatgpt4turbo_preview/request.py b/src/llm/openai/chatgpt4turbo_preview/request.py
new file mode 100644
index 0000000..9753785
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/request.py
@@ -0,0 +1,10 @@
+import json
+
+
+class ModelRequest():
+    def __init__(self, prompt):
+        self.prompt = prompt
+
+    def to_json(self):
+        return json.dumps(self, default=lambda o: o.__dict__,
+                          sort_keys=True, indent=4)
diff --git a/src/llm/openai/chatgpt4turbo_preview/requirements.txt b/src/llm/openai/chatgpt4turbo_preview/requirements.txt
new file mode 100644
index 0000000..ef90739
--- /dev/null
+++ b/src/llm/openai/chatgpt4turbo_preview/requirements.txt
@@ -0,0 +1,7 @@
+aiohttp==3.8.4
+quart
+async-cache==1.1.1
+requests
+openai==0.28
+openai_async==0.0.3
+tenacity
\ No newline at end of file