NVIDIA: Nemotron 3.5 Content Safety (free)
nvidia/nemotron-3.5-content-safety:free- Modalities
- text+image->text
- In / out price
- Free
- Context
- 128K
- Released
- Jun 4, 2026
- Knowledge cutoff
- —
per 1M
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...
FreeVisionReasoningLong context
Supported parameters
include_reasoningInclude reasoning
Include a reasoning summary in the response.
max_tokensMax tokens
Upper bound on generated tokens. Output stops at the limit.
reasoningReasoning
Enable or configure reasoning. The fields differ by model.
seedSeed
A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.
temperatureTemperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.
top_pTop-p
Sample only from tokens whose cumulative probability reaches top_p.