MODEL PROOF
Nemotron 3.5 Content Safety (free)
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
- Independent LMArena score
- Not independently rated
- Context window
- 128K
- Maximum output
- 8.19K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- Free / 1M tokens
- Published output price
- Free / 1M tokens
- Pricing kind
- fixed
MODEL MONUMENT
Save or share this proof
NVIDIA: Nemotron 3.5 Content Safety (free). Balanced workload. Not independently rated. Evidence as of 28 Aug 2026.
Every price dimension
| Input | free/M |
|---|---|
| Output | free/M |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Capability
| Context window | 128K |
|---|---|
| Max output | 8K |
| Input modes | text, image |
| Tool use | no |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-28 |
| Quality data | unrated |
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...
Questions this page answers
What beats Nemotron 3.5 Content Safety (free)?
Nemotron 3.5 Content Safety (free) has no independent quality score. Unrated is not a score of zero.
Does Nemotron 3.5 Content Safety (free) have an independent quality score?
Nemotron 3.5 Content Safety (free) has no independent quality score in this catalogue. Unrated is not a score of zero.
What does Nemotron 3.5 Content Safety (free) cost?
free/M in, free/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does this page use Artificial Analysis scores for Nemotron 3.5 Content Safety (free)?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.