Loading...
Loading...
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.
OpenOCR routes requests to the best provider able to handle your file type and parameters, with fallbacks to maximize uptime.
Benchmark score
Latency
—
Languages
0+
Max Pages
1
Supported Formats
Capabilities
Strengths
Aggregator. OpenOCR routes only to paid tiers in prod; free training tiers are excluded. Per-tier privacy varies upstream.
| Engine | Provider | Benchmark | Price |
|---|---|---|---|
| Datalab Convert (accurate) | Datalab | 77.2%✓ | 100 pages / $1$0.01/page |
| Meta: Llama 4 Maverick | OpenRouter | 71%✓ | ~1,080 pages / $1~$0.000926 per standard page |
| Anthropic: Claude Opus 4.5 | OpenRouter | 67.5%✓ | ~54 pages / $1~$0.0185 per standard page |
| Meta: Muse Spark 1.2 | OpenRouter | 65.5%✓ | ~137 pages / $1~$0.00732 per standard page |
| Mistral: Mistral Medium 3 | OpenRouter | 64.9%✓ | ~662 pages / $1~$0.00151 per standard page |
| OpenAI: GPT-5.6 Luna | OpenRouter | 64.8%✓ | ~770 pages / $1~$0.0013 per standard page |
| Mistral: Mistral Medium 3.1 | OpenRouter | 64.6%✓ | ~662 pages / $1~$0.00151 per standard page |
| Gemini 3 Flash Preview | Google Cloud | 63.6%✓ | ~184 pages / $1~$0.00543 per standard page |
| StepFun: Step 3.7 Flash | OpenRouter | 63.6%✓ | ~1,150 pages / $1~$0.000867 per standard page |
| Anthropic: Claude Opus 4.6 | OpenRouter | 63.4%✓ | ~53.9 pages / $1~$0.0185 per standard page |
| NVIDIA: Nemotron 3.5 Content Safetycurrent | OpenRouter | No hard score | ~3,230 pages / $1~$0.000309 per standard page |
Top 10 by benchmark score, plus this engine. Compare all 177 engines
This engine supports all languages via its underlying AI model. Pass any ISO 639-1 language code to optimize results.