nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

stream = client.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
    messages=[
      {
        "role": "user",
        "content": "Explain quantum computing in simple terms"
      }
    ],
    max_tokens=16000,
    temperature=1,
    top_p=0.95,
    stream=True
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

print("\n")

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://platform.qubrid.com/v1',
  apiKey: 'QUBRID_API_KEY',
});

const stream = await client.chat.completions.create({
  model: 'nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8',
  messages: [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  max_tokens: 16000,
  temperature: 1,
  top_p: 0.95,
  stream: true
});

for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log('\n');

package main

import (
  "bytes"
  "encoding/json"
  "net/http"
)

func main() {
  url := "https://platform.qubrid.com/v1/chat/completions"

  data := {
  "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 1,
  "max_tokens": 16000,
  "stream": true,
  "top_p": 0.95
}
  jsonData, _ := json.Marshal(data)

  req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
  req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
  req.Header.Set("Content-Type", "application/json")

  client := &http.Client{}
  res, _ := client.Do(req)
}