Nemotron 3.5 Content Safety

NVIDIAReasoning

nvidia/nemotron-3.5-content-safetyOpen Weights

Safety model for policy screening, moderation, and risk-aware routing workflows

Benchmark Pricing$0.05 / 1M in$0.15 / 1M out$0.03 cache read

Context: 128,000 tokens•Max Output: 8,192 tokens•Released: 2026-06-02

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens

Max Output8,1928.2K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVision

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Nemotron 3.5 Content Safety does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Nemotron 3.5 Content Safety 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-3.5-content-safety",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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