tokenstat
tokenstat

NVIDIA: Nemotron 3.5 Content Safety

nvidia/nemotron-3.5-content-safety · rates as of · Benchmarks · AI plans · Calculator

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
131K
tokens
Sources
3
10 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $0.2 → $0.15
  • ↓ lowerInput $0.2 → $0.05

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 listings. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestnvidia/nemotron-3.5-content-safety:freeKilo Gateway$0$0$0128K
OpenRouternvidia/nemotron-3.5-content-safety:freeOpenRouter$0$0$0128K
models.devnemotron-3.5-content-safetyRequesty$0$0$0131K
LiteLLMnvidia/nemotron-3.5-content-safety:freeN/A$0$0$0N/A
LiteLLMnemotron-3.5-content-safety:freeN/A$0$0$0N/A
models.devnvidia/nemotron-3.5-content-safetyNanoGPT$0.05$0.15$0.025131K
models.devnvidia/nemotron-3.5-content-safetyKilo Gateway$0.2$0.2$0131K
OpenRouternvidia/nemotron-3.5-content-safetyOpenRouter$0.2$0.2$0.02131K
LiteLLMnvidia/nemotron-3.5-content-safetyN/A$0.2$0.2$0.02N/A
LiteLLMnemotron-3.5-content-safetyN/A$0.2$0.2$0.02N/A

Capabilities

  • Reasoning
  • Attachments
  • Open weights
  • In: text
  • In: image
  • Out: text
Released: 2026-06-04Family: nemotron

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.