NVIDIA

Nemotron 3 Nano 30B

NVIDIA's fast model with reasoning

Text

Reasoning

Tools

Type: Chat
Context: 262K tokens
Russian: low
Input price: 4 ₽ / 1M tokens
Output price: 16 ₽ / 1M tokens
Release date: December 2025

chat/completions

import OpenAI from "openai"
const client = new OpenAI({
  baseURL: "https://api.yenisei.ru/v1",
  apiKey: process.env.YENISEI_API_KEY,
})
const stream = await client.chat.completions.create({
  model: "nemotron-nano-30b",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Nemotron 3 Nano 30B is an NVIDIA model with reasoning support. For complex tasks it switches on step-by-step analysis; on standard ones it stays fast. The model follows instructions, holds conversations confidently and helps with text analysis. It is multilingual, works in Russian and supports tool calling, which is handy for agents and automation.