NVIDIA: Nemotron 3.5 Content Safety
Try Nemotron 3.5 Content Safety for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "nvidia/nemotron-3.5-content-safety"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "nvidia/nemotron-3.5-content-safety"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B, designed to moderate both inputs and outputs of LLMs and VLMs.
It classifies prompts and responses as safe or unsafe across 23 safety categories based on the Aegis v2 taxonomy, supports 12 languages, and accepts both text and image input. An optional reasoning mode provides step-by-step chain-of-thought traces explaining each decision — useful for auditing and policy tuning.
Despite its 4B size, it leads external multimodal safety benchmarks including the top harmful-F1 score on VLGuard, matching or beating 8–12B models. It also supports custom operator-defined content policies enforced at inference time.
Choose it for prompt and response moderation pipelines, safety evaluation of LLM outputs, or as an inference-time guardrail in enterprise AI applications requiring explainable, policy-aware content filtering.
Context Window 131K
tokens
Max Output N/A
tokens
Input Cost $0.05
per million tokens
Output Cost $0.15
per million tokens
Release Date Jun 4, 2026
Try Nemotron 3.5 Content Safety for free
Try Nemotron 3.5 Content Safety instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
More AI Models From NVIDIA
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts model from NVIDIA with 120B total parameters and 12B active per token. It takes text, images, documents, and video, and adds reasoning and tool use for long-running agents. NVIDIA reports results on SWE-bench Verified, SWE-bench Pro, CharXiv reasoning, and OSWorld-Verified, and says it matches Nemotron 3 Ultra on agent tasks with about one-fifth the parameters. It trails newer open models such as Qwen3.8-Flash-Next and DeepSeek-V4-Flash on most coding and agent benchmarks. It has a 1M-token context window. It suits agent workflows that mix tool calls with document, chart, screenshot, or video inputs.
ChatNemotron 3.5 Lightning
Nemotron 3.5 Lightning is a 30B-parameter Mixture-of-Experts model from NVIDIA with 3B active parameters per token, using a hybrid Mamba-2, MoE, and attention layer architecture. It is designed for high-volume, low-latency execution inside multi-agent systems, where a larger reasoning model like Nemotron 3 Ultra plans and delegates, and Lightning handles tool calls, code review, and other repetitive subagent tasks. NVIDIA reports up to 4x higher output throughput than similarly sized open models and, on its PinchBench agent benchmark, 86% accuracy while completing 10,000 tasks 30% faster than Qwen3.6 35B at similar accuracy. The model ships with built-in multi-token prediction and draft models for speculative decoding, and is available in NVFP4 and BF16 checkpoints under the permissive OpenMDW-1.1 license with open weights and training recipes. Choose it for agent harnesses handling frequent, narrow calls, tool validation, or subagent delegation where response speed matters more than broad reasoning depth.
ChatNemotron 3 Ultra 550B A55B
Nemotron 3 Ultra 550B A55B is NVIDIA's open-weight frontier reasoning model with 550B total and 55B active parameters, built on a hybrid Mamba-Transformer Mixture-of-Experts architecture. It supports a 1M token context window and is designed for long-running agentic workflows, complex multi-step reasoning, and high-accuracy tasks across code, math, and science. NVIDIA reports up to 5.9x higher inference throughput than comparable open MoE models. On the Artificial Analysis Intelligence Index it scores 48, leading US open-weight models and delivering the highest non-hallucination score in its comparison set (78.7 on AA-Omniscience). Choose it for production agentic pipelines, deep document analysis, or reasoning-heavy API workloads where both accuracy and throughput matter.
Frequently Asked Questions
You can access Nemotron 3.5 Content Safety by NVIDIA through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Nemotron 3.5 Content Safety is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Nemotron 3.5 Content Safety is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.05 |
| Output | $0.15 |
Nemotron 3.5 Content Safety was created by NVIDIA and released on Jun 4, 2026.
Nemotron 3.5 Content Safety supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Nemotron 3.5 Content Safety can generate up to 0K tokens in a single response.
Yes — the Nemotron 3.5 Content Safety API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Nemotron 3.5 Content Safety to your app for free
Developers can integrate Nemotron 3.5 Content Safety for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.