Nemotron 3.5 Content Safety
- Family
- Nemotron 3.5
- Released
- 2026-06-02
- Context
- 128K
- Parameters
- 4B
- Architecture
- Decoder Only
- Specialization
- moderation
- Openness
- Open weights
- License
- OpenMDW 1.1Commercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 1 route · OpenRouter
About
Nemotron 3.5 Content Safety is NVIDIA's 4B multimodal, multilingual content-safety moderator, fine-tuned from Google Gemma 3 4B IT. It labels user prompts (with an optional image) and model responses as safe or unsafe using the Aegis 2.0 taxonomy, and adds a custom-policy mode that can emit a short reasoning trace. It merges the Nemotron 3 Content Safety and Content Safety Reasoning 4B models, supports 12 languages and up to 128K context, and ships as open weights under OpenMDW 1.1 plus the Gemma Terms of Use.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.200 | $0.200 | Serverless |
Capabilities
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
nvidia/Nemotron-3.5-Content-Safetynvidia/nemotron-3.5-content-safetyCheapest of 1 route · OpenRouter