Legacy · backend
Use GPT-3.5 Turbo with FastAPI
Updated 2026-05-21 · By XALEN
How to use GPT-3.5 Turbo (Legacy, ~175B) with FastAPI. Install, authenticate, and make your first API call in minutes. Working code example included.
Model
GPT-3.5 Turbo
~175B · 16K context · $0.005 input
Framework
FastAPI
backend · pip install xalen fastapi uvicorn
1. Install
pip install xalen fastapi uvicorn
2. Code
from fastapi import FastAPI
from pydantic import BaseModel
from xalen import XALEN
app = FastAPI()
client = XALEN(api_key="xln_test_YOUR_KEY")
class ChatRequest(BaseModel):
messages: list
@app.post("/chat")
async def chat(req: ChatRequest):
response = client.chat.completions.create(
model="gpt-3-5-turbo",
messages=[m.dict() for m in req.messages]
)
return {"reply": response.choices[0].message.content}
GPT-3.5 Turbo with Other Frameworks
Other Models with FastAPI
200+ models. One API. Works with any framework.
Get API KeyLast updated: 2026-05-21