Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Nemotron 3.5 Content Safety (free)

NVIDIA· released 4 Jun 2026

nvidia/nemotron-3.5-content-safety:free
Input / 1M tokens
free
Output / 1M tokens
free
Context window128K tokens

Longest answer: 8K tokens

reads textreads imageopen weightsvisionreasoning
See it on openrouter.ai

About

Nemotron 3.5 Content Safety (free) is NVIDIA’s multimodal guardrail model for moderating both prompts sent to language and vision-language models and their responses. It is a compact model with 4 billion parameters, fine-tuned from Google Gemma-3-4B. It accepts text and image inputs and produces text, with vision and reasoning support. The context window is 128,000 tokens, while the maximum output is 8,192 tokens. The model has open weights and is available under the identifier nvidia/nemotron-3.5-content-safety:free; its Hugging Face identifier is nvidia/Nemotron-3.5-Content-Safety. NVIDIA lists it as free. It was released on June 4, 2026. These details position it for moderation workflows where incoming content and model responses both need guardrail checks.

Who it is for

It suits teams adding content moderation to workflows involving language or vision-language models. Text and image input support may suit pipelines that need to check both kinds of content.

What is good

  • Moderates inputs and model responses.
  • Accepts text and image inputs.
  • Open weights are available.
  • Listed as free.
  • Context window is 128,000 tokens.

What to know first

  • Maximum output is 8,192 tokens.
  • No tool support is listed.

Verdict

Nemotron 3.5 Content Safety is oriented toward moderation rather than general-purpose generation. Its free listing, open weights, and image input are relevant when evaluating a guardrail component.

Details

Lab
NVIDIAopenrouter.ai · 3 Oct 2026
Context
128Kopenrouter.ai · 3 Oct 2026
Input price
Freeopenrouter.ai · 3 Oct 2026
Output price
Freeopenrouter.ai · 3 Oct 2026
Max output
8,192 tokensopenrouter.ai · 3 Oct 2026
Inputs
text, imageopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources