Open Source · backend

Use NVIDIA Nemotron 70B with Flask

Updated 2026-05-21 · By XALEN

1. Install

pip install xalen flask

2. Code

from flask import Flask, request, jsonify
from xalen import XALEN

app = Flask(__name__)
client = XALEN(api_key="xln_test_YOUR_KEY")

@app.route("/chat", methods=["POST"])
def chat():
    data = request.json
    response = client.chat.completions.create(
        model="nvidia-llama-3-1-nemotron-70b",
        messages=data["messages"]
    )
    return jsonify({"reply": response.choices[0].message.content})

if __name__ == "__main__":
    app.run()

NVIDIA Nemotron 70B with Other Frameworks

Other Models with Flask

Last updated: 2026-05-21