---
id: "nvidia/nemotron-3.5-content-safety"
also: ["nvidia/nemotron-3.5-content-safety-20260604", "nvidia/Nemotron-3.5-Content-Safety", "requesty/nvidia/nemotron-3.5-content-safety"]
cheapest_list_usd_per_m: "0.2 in, 0.2 out, at deepinfra/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.1994 in, 0.1974 out, at deepinfra/bf16 on openrouter"
context: 131072
max_output: 117964
input: ["text", "image"]
output: ["text"]
released: "2026-06-04"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p"]
endpoints: 2
gateways: "openrouter (1), requesty (1)"
no_training: 1
trains: 1
retains_prompts: 1
---
# NVIDIA: Nemotron 3.5 Content Safety

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens. Suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. Part of the NVIDIA Nemotron family of open models for agentic AI.