← All models
Balanced — strong quality at a mid priceOpen Weights
Nemotron 3.5 Content Safety Pricing
NVIDIA · nvidia-nemotron-3-5-content-safety
Input / 1M tokens
$0.200
Output / 1M tokens
$0.200
Context window
131,072 tokens
≈ 175 pages of text
Max output
117,964 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0003
1,000 requests / month$0.32/mo10,000 requests / month$3.20/mo100,000 requests / month$32.00/moEstimate your own workloadOpens the calculator with Nemotron 3.5 Content Safety preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Strong on content moderation and safety classification for text and vision inputs. Supports 128k context at low per-token cost.
The business tradeoff
Specialized safety focus limits general reasoning performance. Open weights introduce hosting and consistency variance.
Cheaper from NVIDIA
Head-to-head
Vendor list rates, as of Sep 4, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.