Nemotron 3.5 Content Safety
NVIDIA · Open weights · Released Jun 4, 2026 · nvidia/nemotron-3.5-content-safety
Best $0.20 in / $0.20 out via DeepInfra · bf16
131K contextVisionReasoningOpen weights
Available from 1 providerUSD / MTOK · PRICES 24 MINUTES AGO · SPEED 14 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.20 | $0.20 | — | 131K | bf16 | ✕ | ✕ | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 14 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.20 / $0.20
per MTok in / out
FREE
Free / Free
per MTok in / out
Recent changesRSS ↗
Sep 4, 2026model added
About
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...
Specifications
Context window131,072
Max output117,964
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedJun 4, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/nvidia/nemotron-3.5-content-safety)Sources
OpenRouter API24 minutes ago
AGGREGATORHugging Face24 minutes ago
COMMUNITYModelIndex benchmarks14 days ago
MEASUREDVerified 24 minutes ago · list prices, not negotiated rates.