Skip to main content
Use Passy’s OpenAI-compatible API with FastAPI using the modern uv package manager for fast Python dependency management.

​
What is uv?

uv is an extremely fast Python package installer and resolver, written in Rust. It’s a drop-in replacement for pip that’s 10-100x faster.

​
Prerequisites

  • Python 3.9+ installed
  • An Passy account with an API key

​
Installation

1

​
Install uv

curl -LsSf https://astral.sh/uv/install.sh | sh
2

​
Create Project

Create a new project directory and initialize:
mkdir passy-fastapi && cd passy-fastapi
uv init
3

​
Install Dependencies

uv add fastapi uvicorn openai python-dotenv
This creates a pyproject.toml and installs dependencies in a virtual environment.
4

​
Set Environment Variables

Create a .env file:
PASSY_API_KEY=your-api-key-here
PASSY_BASE_URL=https://api.passy.ai/v1

​
Create the Application

1

​
Create the Passy Client

# passy_client.py
import os
from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()

passy = OpenAI(
    api_key=os.getenv("PASSY_API_KEY"),
    base_url=os.getenv("PASSY_BASE_URL"),
)
2

​
Create the FastAPI App

# main.py
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from passy_client import passy

app = FastAPI(title="Passy FastAPI")

class ChatRequest(BaseModel):
    message: str
    model: str = "gpt-4o"

class ChatResponse(BaseModel):
    reply: str

@app.post("/chat", response_model=ChatResponse)
async def chat(request: ChatRequest):
    try:
        completion = passy.chat.completions.create(
            model=request.model,
            messages=[{"role": "user", "content": request.message}],
        )
        return ChatResponse(reply=completion.choices[0].message.content)
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/chat/stream")
async def chat_stream(request: ChatRequest):
    async def generate():
        stream = passy.chat.completions.create(
            model=request.model,
            messages=[{"role": "user", "content": request.message}],
            stream=True,
        )
        for chunk in stream:
            content = chunk.choices[0].delta.content
            if content:
                yield content

    return StreamingResponse(generate(), media_type="text/plain")

@app.get("/health")
async def health():
    return {"status": "healthy"}
3

​
Run the Server

uv run uvicorn main:app --reload
Your API is now running at http://localhost:8000Test it with:
curl -X POST http://localhost:8000/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello!"}'

​
Project Structure

passy-fastapi/
├── .env
├── .python-version
├── pyproject.toml
├── uv.lock
├── passy_client.py
└── main.py

​
Advanced: Async Client

For better performance with FastAPI’s async nature: 
# passy_client.py
import os
from dotenv import load_dotenv
from openai import AsyncOpenAI

load_dotenv()

passy = AsyncOpenAI(
    api_key=os.getenv("PASSY_API_KEY"),
    base_url=os.getenv("PASSY_BASE_URL"),
)

# main.py (async version)
@app.post("/chat", response_model=ChatResponse)
async def chat(request: ChatRequest):
    completion = await passy.chat.completions.create(
        model=request.model,
        messages=[{"role": "user", "content": request.message}],
    )
    return ChatResponse(reply=completion.choices[0].message.content)

​
Available Models

Use any Passy supported model: 
# Popular choices
model = "gpt-4o"           # Fast and capable
model = "gpt-5"            # Most powerful
model = "claude-sonnet-4-5" # Anthropic's latest

​
Need Help?

WhatsApp Support

Chat with us instantly

Book a Call

For enterprise support