Skip to content

NVIDIA · Chat

Nemotron 3.5 Content Safety

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.
From Aiml API's listing:
NVIDIA Nemotron 3.5 Content Safety is a multimodal guard model from the Nemotron 3.5 family that classifies text and image content against safety policies, intended for moderating prompts and model responses rather than open-ended generation.
Market median price
$0.20 blended / 1M
Max context
131K
Listings
14
Providers
10

Evidence and sources

🤗 nvidia/Nemotron-3.5-Content-SafetyReleased 22 May 2026Maker HQ: US (source)
All rankings: #13 in Google Trends interest this week #378 on OpenRouter this month #401 on NanoGPT recently #483 on OpenRouter this week #512 on OpenRouter todayAll rankings: #13 in Google Trends interest this week #378 on OpenRouter this month #401 on NanoGPT recently #483 on OpenRouter this week #512 on OpenRouter todaySources: DeepInfra data, NVIDIA NIM data, Models.dev data, AI/ML API data, Hugging FacePrimary data from DeepInfra from NVIDIA NIM: name from Models.dev: weights availability from AI/ML API: primary mode, description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative chat models

Advantages

Open weights available

The weights are public. 4 of the 10 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningStructured outputPrompt caching

Listings

 Fastrouternvidia/nemotron-content-safety-3.5Source: FastRouter data131K$0.20$0.20——
 Flowdotnvidia/nemotron-3.5-content-safety:free · freeSource: FlowDot data128K$0.00$0.00——
 Flowdotnvidia/Nemotron-Content-Safety-3.5Source: FlowDot data131K$0.20$0.20——
 Kilonvidia/nemotron-3.5-content-safetySources: Kilo AI Gateway data, Models.dev data131K$0.20$0.20——
 NanoGPTnvidia/nemotron-3.5-content-safetySources: Models.dev data, NanoGPT131K$0.05cache read $0.025$0.15——
 NanoGPTInference by AoruRegions: 🇰🇷 KRnvidia/nemotron-3.5-content-safety · FP8Source: NanoGPTNot published by the provider$0.0525cache read $0.0263$0.1575——
 NanoGPTInference by DeepInfraRegions: 🇺🇸 USnvidia/nemotron-3.5-content-safety · bf16Source: NanoGPTNot published by the provider$0.21$0.21——
 OpenRouterInference by DeepInfranvidia/nemotron-3.5-content-safety · bf16Source: OpenRouter data docs131K$0.20$0.20164115ms
 OpenRouternvidia/nemotron-3.5-content-safetySources: Models.dev data, OpenRouter data docs131K$0.20$0.20——
 DeepInfranvidia/Nemotron-Content-Safety-3.5 · bf16Sources: DeepInfra data, LiteLLM data131K$0.20$0.20——
 Vultrnemotron-3.5-content-safetySources: Models.dev data, Vultr Serverless Inference data131K$0.05$0.15——

3 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

No benchmark scores yet.

Also known as: deepinfra/nvidia/nemotron-content-safety-3.5, nemotron-3.5-content-safety-free, nemotron-content-safety-3.5, nvidia/nemotron-3.5-content-safety, nvidia/nemotron-3.5-content-safety:free, nvidia/nemotron-content-safety-3.5, nvidia_nim/nvidia/nemotron-3.5-content-safety

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works