Nemotron Content Safety 3.5
4039°
nvidia | 131,072 token context | $0.20/M input, $0.20/M output. Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.
Guides for this model
All guides
Captain's notes
Notes from 2026-10-13
Nemotron Content Safety 3.5 is a multimodal safety classifier from NVIDIA that handles both text and images. It returns a safe/unsafe verdict alongside a reasoning trace, and supports custom policies, making it more flexible than a fixed-rule filter. It suits teams building guardrails into LLM pipelines, running safety evaluations, or post-training models for safer behavior.
Known for
- Classifies both text and images, not text alone
- Returns a reasoning trace alongside every safe/unsafe verdict
- Supports custom safety policies beyond a fixed default ruleset
- Usable as an inference-time guardrail or an LLM safety judge
- Ships with a training dataset for post-training safer model behavior
Watch out for
- Weights are not open; you access it via API only, no local deployment.
- Pricing and context are published, but licence terms for the training dataset are not detailed publicly.
Best for
Prompts to try
Test a custom safety policy
You are evaluating content for a children's educational platform. The policy prohibits violence, adult themes, and strong language. Classify the following text as safe or unsafe under that policy, and explain your reasoning step by step: 'The hero grabbed the villain by the throat and threatened to make him disappear permanently.'
Evaluate an LLM response
A user asked an AI assistant how to pick a lock. The assistant replied: 'Lock picking is a skill used by locksmiths. You insert a tension wrench, apply light rotational pressure, then use a pick to set each pin. With practice, most pin tumbler locks open in under a minute.' Classify this response as safe or unsafe and trace your reasoning.
Batch safety audit
I have five customer-support replies generated by an LLM. For each one, return a safe or unsafe classification and a one-sentence reason. Reply 1: 'I understand your frustration.' Reply 2: 'Just kill the process and restart.' Reply 3: 'Your account will be terminated.' Reply 4: 'Happy to help with that.' Reply 5: 'You people never read the instructions.'
Compare with
- Claude Opus 5.5API-only model1,000,000 token context · $4.00/M input, $20.00/M output
- Gemini 3.1 Flash LiteAPI-only model1,048,576 token context · $0.25/M input, $1.50/M output
- Claude Fable 5.1API-only model1,000,000 token context · $10.00/M input, $50.00/M output
- GPT-6 AstraAPI-only model1,050,000 token context · $10.00/M input, $50.00/M output
More text models from nvidia
Questions people ask
- Can I run Nemotron Content Safety 3.5 locally?
- No. The weights are not open and there is no Hugging Face repository; you access it through NVIDIA's API only.
- What does it cost and what is the context window?
- NVIDIA charges $0.20 per million input tokens and $0.20 per million output tokens, with a 131,072-token context window.
- How is this different from a standard content-moderation API?
- Unlike a fixed-category filter, Nemotron Content Safety 3.5 accepts custom policies, handles images as well as text, and returns a reasoning trace rather than just a label, which makes it more useful as a judge in safety evaluation pipelines.
Captain's verdictA practical choice if you need a transparent, policy-flexible safety layer over an LLM pipeline and do not require open weights.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Nemotron Content Safety 3.5 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153