Nemotron 3.5 Content Safety

NVIDIA· released 4 Jun 2026

nvidia/nemotron-3.5-content-safety

Input / 1M tokens: $0.2
Output / 1M tokens: $0.2

Context window131K tokens

Longest answer: 118K tokens

reads textreads imageopen weightsvisionreasoning

About

Nemotron 3.5 Content Safety is NVIDIA’s 4-billion-parameter guardrail model for moderating content sent to and returned by language and vision-language models. It accepts text and images, and produces text. The model is multimodal, supports vision, and has a 131,072-token context window with a maximum output of 117,964 tokens. NVIDIA fine-tuned it from Google Gemma-3-4B. Its weights are open, and its Hugging Face identifier is nvidia/Nemotron-3.5-Content-Safety. The model supports reasoning. Listed input pricing is $0.20 per 1M tokens, and output pricing is $0.20 per 1M tokens. It was released on June 4, 2026. For teams routing model traffic through moderation, the combination of image and text inputs and its guardrail role define its fit; the listed facts do not specify moderation categories or deployment requirements.

Who it is for

It suits teams that need to moderate text and image inputs to, or responses from, LLMs and VLMs. Open weights may also suit teams looking to work with an open-weight model.

What is good

Moderates inputs and responses for LLMs and VLMs
Accepts text and image inputs
Open weights
131,072-token context window
$0.20 per 1M input and output tokens

What to know first

Text-only output
Maximum output is 117,964 tokens

Verdict

Nemotron 3.5 Content Safety is a focused moderation model with text and image inputs, open weights, and a 131,072-token context. Its listed input and output prices are both $0.20 per 1M tokens.

Details

Lab: NVIDIAopenrouter.ai · 3 Oct 2026
Context: 131Kopenrouter.ai · 3 Oct 2026
Input price: $0.2 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.2 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 117,964 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, imageopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash ctx262KinFreeoutFree inclusionAI Apodex 1.1 Mini (free) ctx262KinFreeoutFree Apodex Pareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiased GPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI GPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI Claude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed
NVIDIA Models: Pricing per 1M Tokens and Context (2026)11 listed

Sources

openrouter.ai/nvidia/nemotron-3.5-content-safety· checked 3 Oct 2026