Modeldex
Drag to turnCard front showing

NVIDIASafetyCommon

Nemotron 3.5 Content Safety

Safety model for policy screening, moderation, and risk-aware routing workflows

nvidia/nemotron-3.5-content-safety
Type
Safety
Quality
Not rated yet
Context window
128,000 tokens
Max output
8,192 tokens
Input price
Free
Output price
Not billed
Cache read
—
Cache write
—
Parameters
4.3B (4,300,079,472)
Downloads
24K in the last 30 days
Likes
63
Access to weights
Open download
Released
Jun 4, 2026
Knowledge cutoff
—
Takes in
Text, Image
Puts out
Text
Reasoning
Yes
Tool calling
No
Structured output
No
File attachments
Yes
Access
Free
License
OpenMDW License Agreement
Rarity
Common
Set number
916/1040
Open NVIDIA docsWeights on Hugging FaceWhere to run it 7Evolution 2/2Meet its creatureBattle wildguard

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: docs.api.nvidia.com.

How good is it?

Public leaderboard scores for Nemotron 3.5 Content Safety, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Nemotron 3.5 Content Safety yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

7 providers sell Nemotron 3.5 Content Safety through an API. Prices are per million tokens, cheapest first.

API providers

ProviderPriceContext
AIHubMixFreenemotron-3.5-content-safety-freeFree128K
Kilo GatewayFreenvidia/nemotron-3.5-content-safety:freeFree128K
NvidiaOfficialFreenvidia/nemotron-3.5-content-safetyFree128K
OpenRouterFreenvidia/nemotron-3.5-content-safety:freeFree128K
RequestyFreenemotron-3.5-content-safetyFree131K
NanoGPTCheapest paidnvidia/nemotron-3.5-content-safety$0.05131K
Vultrnemotron-3.5-content-safety$0.05131K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from NVIDIA

NVIDIA

Nemotron 3.5 Super VL 120B A12B

CTX1.05M
New
Reasoning · Vision · Tools
TextImageVideoInputFree
TextOutputFree

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

FreeNVIDIA Open Model license1037/1040
NVIDIA

Nemotron 3.5 Lightning 30B A3B

CTX262K
Reasoning · Tools
TextInputFree
TextOutputFree

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

FreeNVIDIA Open Model license975/1040
NVIDIA

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

SIZE32B
Text
TextDownloads32K/mo
TextLikes25

Language model from NVIDIA, 32B parameters.

Open weightsOpenMDW 1.1 license965/1040
NVIDIA

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

SIZE32B
Text
TextDownloads690K/mo
TextLikes240

Language model from NVIDIA, 32B parameters.

Open weightsOpenMDW 1.1 license960/1040
NVIDIA

Nemotron-3-Embed-8B-BF16

SIZE8B
Embedding
TextDownloads110K/mo
–Likes110

Sentence embedding model from NVIDIA, 8B parameters.

Open weightsOpenMDW 1.1 license948/1040
NVIDIA

Nemotron-3-Embed-1B-BF16

SIZE1.1B
Embedding
TextDownloads220K/mo
–Likes170

Sentence embedding model from NVIDIA, 1.1B parameters.

Open weightsOpenMDW 1.1 license947/1040
NVIDIA

NVIDIA-Nemotron-Parse-2.0

SIZE903M
Vision
TextImageDownloads19K/mo
TextLikes120

Vision-language model from NVIDIA, 903M parameters.

Open weightsOpenMDW 1.1 license938/1040
NVIDIA

Nemotron 3 Ultra 550B A55B

CTX1M
Reasoning · Tools
TextInput$0.50/M
TextOutput$2.50/M

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Open weightsNVIDIA Open Model license915/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot