Skip to content
OpenOCR
ONVIDIA

NVIDIA: Nemotron 3.5 Content Safety

$0.00022/page

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...

Try itCompare

Providers for NVIDIA: Nemotron 3.5 Content Safety

OpenOCR routes requests to the best provider able to handle your file type and parameters, with fallbacks to maximize uptime.

OOpenRouter
☁️ CloudComing Soon
Latency
—
Throughput
—
Price/page
$0.00022/page
Max pages/req
1
Formatspngjpgjpegwebpgif
Specifications

Benchmark score

—

Latency

—

Languages

0+

Max Pages

1

Supported Formats

pngjpgjpegwebpgif

Capabilities

printed-texthandwritingmulti-languagelayout-analysisscene-text
Strengths & Weaknesses

Strengths

  • large-context-window
  • cost-effective
Data Privacy
No data trainingglobal
Data retentionRetention unknown

Aggregator. OpenOCR routes only to paid tiers in prod; free training tiers are excluded. Per-tier privacy varies upstream.

Privacy policy
Engine Comparison
EngineProviderBenchmarkPrice/Page
Mistral OCR 4Mistral AI84.8%✓$0.005/page
Meta: Llama 4 MaverickOpenRouter71%✓$0.00036/page
Anthropic: Claude Opus 4.5OpenRouter67.5%✓$0.0085/page
Meta: Muse Spark 1.2OpenRouter65.5%✓$0.0095/page
Mistral: Mistral Medium 3OpenRouter64.9%✓$0.0008/page
OpenAI: GPT-5.6 LunaOpenRouter64.8%✓$0.0017/page
Mistral: Mistral Medium 3.1OpenRouter64.6%✓$0.00078/page
StepFun: Step 3.7 FlashOpenRouter63.6%✓$0.00064/page
Gemini 3 Flash PreviewGoogle Cloud63.6%✓~$0.0008/page
Anthropic: Claude Opus 4.6OpenRouter63.4%✓$0.0087/page

Top 10 by benchmark score. Compare all 129 engines

Language Support

This engine supports all languages via its underlying AI model. Pass any ISO 639-1 language code to optimize results.

Trust & Privacy
Data Retention
Not disclosed
Trains on Your Data
No
Privacy

Engine Info

Provider
OpenRouter
Engine ID
openrouter/nvidia/nemotron-3.5-content-safety
Status
🔜 Coming Soon