Nemotron Nano 9B v2

NVIDIAMCP Tool CallReasoning

nvidia/nemotron-nano-9b-v2Open Weights

Compact Nemotron model for efficient reasoning and deployable AI agents

Benchmark Pricing$0.06 / 1M in$0.23 / 1M out

Context: 131,072 tokens•Max Output: 131,072 tokens•Knowledge: 2024-09•Released: 2025-08-18

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output131,072131.1K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Nemotron Nano 9B v2 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Nemotron Nano 9B v2 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NVIDIA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "nvidia/nemotron-nano-9b-v2",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);