NVIDIA Nemotron 3 Super 120B
NVIDIA Nemotron 3 Super 120B A12B model for long-context language and agent workloads.
- Input price
- $0.165
- Output price
- $0.715
- Context
- 262K
- Max output
- 131K
- Human preference
- 1377
- 30-day uptime
- —
- Released
- 2024-12-01
InputTextOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
All prices for this model, by service tier.
| Item | Standard | Standard Discount | Priority | Priority Discount | Flex | Flex Discount | |||
|---|---|---|---|---|---|---|---|---|---|
| Inputper 1M tokens | $0.165 | $0.288752 | $0.0825 | ||||||
| Outputper 1M tokens | $0.715 | $1.251252 | $0.3575 | ||||||
| Cache readper 1M tokens | $0.165 | $0.288752 | $0.0825 | ||||||
| Estimated cost of common use (500 output tokens each) | |||||||||
| One chat message3K input tokens | $0.000856 | $0.0015 | $0.000428 | ||||||
| Agent first turn100K tokens of context, none cached | $0.0169 | $0.0295 | $0.00843 | ||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.0172 | $0.0301 | $0.0086 | ||||||
| 20-turn agent taskfirst turn plus 19 more | $0.344 | $0.601 | $0.172 | ||||||
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text