All models
NVIDIA
Nemotron 3.5 Content Safety fastruns locally
nvidia/nemotron-3-5-content-safety
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...
Input / 1M
$0.20
USD per million tokens
Output / 1M
$0.20
USD per million tokens
Est. cost / token
$0.0000002
$0.20 per 1M, 3:1 mix
Context window
131K
max output 118K
Major features
VisionOpen weightsReasoning
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 3.3 GB |
| Q3_K_M | fair | 3.6 GB |
| Q4_K_Mrecommended | good | 4.2 GB |
| Q5_K_M | very good | 4.6 GB |
| Q6_K | excellent | 5.1 GB |
| Q8_0 | near-lossless | 6.2 GB |
| F16 | lossless | 10.5 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.20 | $0.20 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.20
- Output
- $0.20
- Blended (3:1)
- $0.20
Details
- Company
- NVIDIA
- Version
- 3.5
- Family
- Nemotron
- Released
- 2026-06-04
- Parameters
- 4.3B
- Max output
- 118K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 46 min ago