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...
Context
131,072
Max output
117,964
Input / 1M
$0.20
Output / 1M
$0.20
Providers
3
01Profile
Profile
Released
2026-06-04
Last updated
2026-06-04
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
No
Structured output
No
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
7+ recent events since 2026-06-04
2026-09-04Addedkilooffering→ new
2026-09-04Addedopenrouteroffering→ new
2026-08-18Addedrequestyoffering→ new
2026-08-02Addedkilooffering→ new
2026-06-07ContextopenrouterContext window128,000→ new
2026-06-07ContextopenrouterMax output8,192→ new
2026-06-04Addedopenrouteroffering→ new