Llama 3.1 Nemotron Ultra 253B

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key="YOUR_NVIDIA_API_KEY",
)
reply = client.chat.completions.create(
    model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://integrate.api.nvidia.com/v1",
  apiKey: process.env.NVIDIA_API_KEY,
});
const reply = await client.chat.completions.create({
  model: "nvidia/llama-3.1-nemotron-ultra-253b-v1",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);