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...
With CoreAI, you can start chatting with NVIDIA: Nemotron 3.5 Content Safety instantly — no separate subscription needed. CoreAI lets you chat with NVIDIA: Nemotron 3.5 Content Safety alongside 300+ other AI models from NVIDIA and other providers like OpenAI, Anthropic, Google, Meta, and more.
Measured against all 412 chat models CoreAI serves, NVIDIA: Nemotron 3.5 Content Safety sits at #294 for context capacity — 131K tokens, roughly 98,304 words or 197 pages of text in a single conversation. On price, it is the #100 cheapest of 134 budget-tier models by input cost. It joined the catalog on 2026-06-04. It supports step-by-step reasoning (thinking mode) and accepts image input.
Every model in this table is available on CoreAI — open the web app and run the same prompt through NVIDIA: Nemotron 3.5 Content Safety and NVIDIA: Nemotron 3 Super side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00030 on NVIDIA: Nemotron 3.5 Content Safety's raw per-token rates; a heavy session with a 50K-token document costs about $0.011. On CoreAI you don't juggle these numbers — one subscription covers NVIDIA: Nemotron 3.5 Content Safety and 300+ other models under a plan usage limit, with no API keys. See plans.
NVIDIA: Nemotron 3.5 Content Safety handles 131K tokens of context — roughly 98,304 words, or about 197 pages of text in one conversation.
NVIDIA: Nemotron 3.5 Content Safety's underlying rates are $0.2 per 1M input tokens and $0.2 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
Yes — NVIDIA: Nemotron 3.5 Content Safety accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.
Yes. NVIDIA: Nemotron 3.5 Content Safety can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.
Open the CoreAI web app or the iOS/Android app, pick NVIDIA: Nemotron 3.5 Content Safety in the model selector, and chat — no API key, no per-token billing. One subscription covers NVIDIA: Nemotron 3.5 Content Safety and 300+ other models.
The closest alternatives on CoreAI are NVIDIA: Nemotron 3 Super, IBM: Granite 4.2 8B, IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with NVIDIA: Nemotron 3.5 Content Safety and 300+ other AI models — all in one app.