How to beginner · 3 min read

How to use Gemini API with FastAPI

Q: How to use Gemini API with FastAPI

Use the OpenAI SDK v1 to call the Gemini API within a FastAPI app by importing OpenAI, initializing the client with your API key from os.environ, and creating chat completions with client.chat.completions.create(model="gemini-1.5-pro", messages=[...]). This enables building AI-powered endpoints efficiently.

Quick answer

Use the OpenAI SDK v1 to call the Gemini API within a FastAPI app by importing OpenAI, initializing the client with your API key from os.environ, and creating chat completions with client.chat.completions.create(model="gemini-1.5-pro", messages=[...]). This enables building AI-powered endpoints efficiently.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install fastapi uvicorn openai>=1.0

Setup

Install the required packages and set your OpenAI API key as an environment variable.

Install FastAPI, Uvicorn, and OpenAI SDK:

bash

pip install fastapi uvicorn openai>=1.0

Step by step

Create a FastAPI app that uses the OpenAI SDK v1 to call the Gemini API for chat completions. The example below defines a POST endpoint /chat that accepts user messages and returns Gemini's response.

python

import os
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from openai import OpenAI

app = FastAPI()
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

class ChatRequest(BaseModel):
    messages: list[dict]

@app.post("/chat")
async def chat_completion(request: ChatRequest):
    try:
        response = client.chat.completions.create(
            model="gemini-1.5-pro",
            messages=request.messages
        )
        return {"response": response.choices[0].message.content}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

# To run: uvicorn filename:app --reload

Common variations

You can use async calls with FastAPI naturally. To switch models, change model="gemini-1.5-pro" to another Gemini or OpenAI model like gemini-2.0-flash. For streaming responses, integrate FastAPI's StreamingResponse with the SDK's streaming interface.

python

from fastapi.responses import StreamingResponse

@app.post("/chat_stream")
async def chat_stream(request: ChatRequest):
    def event_stream():
        response = client.chat.completions.create(
            model="gemini-1.5-pro",
            messages=request.messages,
            stream=True
        )
        for chunk in response:
            yield chunk.choices[0].delta.get('content', '')

    return StreamingResponse(event_stream(), media_type="text/event-stream")

Troubleshooting

If you get KeyError for the API key, ensure OPENAI_API_KEY is set in your environment.
For Model not found errors, verify the model name is correct and available in your account.
Timeouts or network errors may require retry logic or checking your internet connection.

✅

Key Takeaways

Use the OpenAI SDK v1 with client.chat.completions.create to call Gemini models in FastAPI.
Always load your API key securely from os.environ to avoid exposing secrets.
Switch Gemini models by changing the model parameter for different capabilities.
Implement streaming with FastAPI's StreamingResponse and the SDK's stream=True option.
Handle common errors by validating environment variables and model names before requests.

Verified 2026-04 · gemini-1.5-pro, gemini-2.0-flash

Verify ↗