← All models
Balanced — strong quality at a mid priceOpen Weights
Nemotron 3.5 Super VL Pricing
NVIDIA · nvidia-nemotron-3-5-super-vl
Input / 1M tokens
$0.150
Output / 1M tokens
$0.500
Context window
1,048,576 tokens
≈ 1,398 pages of text
Max output
235,929 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0004
1,000 requests / month$0.38/mo10,000 requests / month$3.80/mo100,000 requests / month$38.00/moEstimate your own workloadOpens the calculator with Nemotron 3.5 Super VL 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 performance on long-context multimodal tasks, supported by a 1M-token window and open-weights availability for custom deployment.
The business tradeoff
Quality depends on self-hosted infrastructure; generally trails closed frontier models on complex multi-step reasoning.
Cheaper from NVIDIA
Head-to-head
Vendor list rates, as of Oct 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.