How to beginner · 3 min read

How to use Claude API with Flask

Q: How to use Claude API with Flask

Use the anthropic Python SDK with Flask by initializing the Anthropic client with your API key from os.environ. Create a Flask route that calls client.messages.create with your chosen Claude model and user messages, then return the AI response in your web app.

Quick answer

Use the anthropic Python SDK with Flask by initializing the Anthropic client with your API key from os.environ. Create a Flask route that calls client.messages.create with your chosen Claude model and user messages, then return the AI response in your web app.

PREREQUISITES

Python 3.8+
Anthropic API key
pip install anthropic flask

Setup

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

Install packages: pip install anthropic flask
Set environment variable in your shell: export ANTHROPIC_API_KEY='your_api_key_here'

bash

pip install anthropic flask

Step by step

Create a simple Flask app that uses the Anthropic SDK to send a prompt to Claude and returns the response.

python

import os
from flask import Flask, request, jsonify
import anthropic

app = Flask(__name__)

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

@app.route('/chat', methods=['POST'])
def chat():
    user_input = request.json.get('message', '')
    if not user_input:
        return jsonify({'error': 'No message provided'}), 400

    response = client.messages.create(
        model="claude-3-5-sonnet-20241022",
        max_tokens=500,
        system="You are a helpful assistant.",
        messages=[{"role": "user", "content": user_input}]
    )

    return jsonify({'response': response.content[0].text})

if __name__ == '__main__':
    app.run(debug=True, port=5000)

output

 * Running on http://127.0.0.1:5000/ (Press CTRL+C to quit)

# Example POST request to http://127.0.0.1:5000/chat with JSON {"message": "Hello Claude!"}
# Response JSON: {"response": "Hello! How can I assist you today?"}

Common variations

You can customize your Flask + Claude integration by:

Using different Claude models like claude-3-5-haiku-20241022 for shorter responses.
Adding async support with asyncio and an async web framework like FastAPI.
Streaming responses by handling partial outputs if supported by the SDK.

Troubleshooting

If you get an authentication error, verify your ANTHROPIC_API_KEY environment variable is set correctly.
For timeout errors, increase max_tokens or check your network connection.
If Flask returns 400, ensure your POST request includes valid JSON with a message field.

✅

Key Takeaways

Use the Anthropic SDK v0.20+ with Flask by importing and initializing the client with your API key from environment variables.
Create a Flask POST endpoint that sends user input to Claude using client.messages.create and returns the AI's response.
Customize your integration by switching Claude models or adopting async frameworks like FastAPI for better performance.
Always handle errors such as missing API keys or invalid requests to ensure a robust Flask app.

Verified 2026-04 · claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022

Verify ↗