NVIDIA
Nemotron 3.5 Content Safety
Released 2026-06-04
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...
You send / 1M
$0.200
tokens in
It replies / 1M
$0.200
tokens out
Memory
131K
tokens it can read at once
Typical request
Free
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · bf16 | $0.200 | $0.200 | 98% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Reasoning: Yes
- Tool calling: No
- Longest reply: 118K tokens
Similar models
- Muse Spark 1.3 ContributorMeta · $0.100 in / $0.200 out per 1M
- Muse Spark 1.2 ContributorMeta · $0.100 in / $0.200 out per 1M
- Ling 3.0 Flash VLInclusionai · $0.060 in / $0.180 out per 1M
- Nex-N2.5-ProNex Agi · $0.075 in / $0.250 out per 1M
- Qwen3.5-9BQwen · $0.170 in / $0.250 out per 1M
- Gemma 4 26B A4B Google · $0.076 in / $0.255 out per 1M
Appears in
Top Free AI ModelsTop Free No-Training AI ModelsTop Free No-Training Zero Data Retention AI ModelsTop Free No-Training Vision AI ModelsTop Free No-Training Reasoning AI ModelsTop Free Zero Data Retention AI ModelsTop Free Zero Data Retention Vision AI ModelsTop Free Zero Data Retention Reasoning AI Models
Estimate your monthly cost with Nemotron 3.5 Content Safety →