← All models
Balanced — strong quality at a mid priceOpen Weights
Nemotron 3 Super Pricing
NVIDIA · nvidia-nemotron-3-super-120b-a12b
Input / 1M tokens
$0.085
Output / 1M tokens
$0.400
Context window
1M tokens
≈ 1,333 pages of text
Max output
16,384 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0003
1,000 requests / month$0.262/mo10,000 requests / month$2.62/mo100,000 requests / month$26.20/moEstimate your own workloadOpens the calculator with Nemotron 3 Super preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Strong long-context processing up to 1M tokens; open weights enable customization and on-premise deployment for domain-specific workloads.
The business tradeoff
Output token pricing is five times input; inference latency and throughput depend entirely on user-managed hosting infrastructure.
Cheaper from NVIDIA
Head-to-head
Vendor list rates, as of Jul 24, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.