NNVIDIA · Released Jun 4, 2026
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...
- Released
- Jun 4 2026
- Context window
- 131K 118K out
- Input / 1M tokens
- $0.20 from Free
- Output / 1M tokens
- $0.20 from Free
Where to run it
7 providers compared
Free to try on Nvidia, Kilo Gateway, Requesty, AIHubMix — free endpoints are often limited-time and rate-limited. Cheapest: NanoGPT, Vultr at $0.05 / $0.15 per 1M input / output tokens — 63% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Nvidiafree · may be limited-time · no tool calling | Free | Free | — | 128K | 8K | 99.8%24h | Free |
| Kilo Gatewayfree · may be limited-time · no tool calling | Free | Free | — | 128K | 8K | — | Free |
| Requestyfree · may be limited-time · no tool calling | Free | Free | — | 131K | 8K | — | Free |
| AIHubMixfree · may be limited-time · no tool calling | Free | Free | — | 128K | 8K | — | Free |
| NanoGPTno tool calling | $0.05 | $0.15 | $0.025 | 131K | 33K | — | Cheapest |
| Vultrno tool calling | $0.05 | $0.15 | — | 131K | 8K | — | Cheapest |
| DeepInfraBF16 · no tool calling | $0.20 | $0.20 | — | 131K | 118K | 100%24h | +167% |
| Kilo Gatewayno tool calling | $0.20 | $0.20 | — | 131K | 118K | — | +167% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nemotron 3.5 Content Safety. Scores appear here automatically once it does.
Specs
Details
- Model ID
nvidia/nemotron-3.5-content-safety- Developer
- NVIDIA
- Release date
- Jun 4, 2026 ·
- Context window
- 131,072 tokens
- Max output
- 117,964 tokens
- API price
- $0.20 / $0.20 per 1M input / output tokens
- Providers
- 7
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- No
- Open weights
- Yes
- Free tier
- Yes
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.