Nemotron 3 Super 120B A12B
As of Nov 22, 2026, the cheapest Nemotron 3 Super 120B A12B API price is $0.06 per 1M input tokens (Kilo Gateway) and $0.32 per 1M output tokens (Kilo Gateway). Nemotron 3 Super 120B A12B is offered by 13 providers in the nemotron-super family, open weights, reasoning enabled. One provider lists it as a free-tier offer.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| Kilo Gatewayopennvidia/nemotron-3-super-120b-a12b | Cheapest$0.06 | Cheapest$0.32 | — | — | 262k | 7d agoout −20% |
| Eden AIopendeepinfra/nemotron-3-super-120b-a12b | $0.075 | $0.4 | — | — | 262k | 18d agoout +0% |
| OpenRouteropennvidia/nemotron-3-super-120b-a12b | $0.075 | $0.4 | — | — | 262k | 15d agoout −83.3% |
| Kenariopennemotron-3-super-120b-a12b | $0.0971 | $0.48 | $0.0097 | — | 262k | 5d agoout +0% |
| Requestyopennvidia-nemotron-3-super-120b-a12b | $0.1 | $0.5 | — | — | 262k | — |
| Boundlessopennemotron3-super | $0.12 | $0.52 | $0.06 | — | 262k | — |
| Amazon Bedrockopennvidia.nemotron-super-3-120b | $0.15 | $0.65 | — | — | 262k | — |
| Vercel AI Gatewayopennvidia/nemotron-3-super-120b-a12b | $0.15 | $0.65 | — | — | 256k | — |
| Eden AIopennebius/nvidia/nemotron-3-super-120b-a12b | $0.3 | $0.9 | $0.3 | — | 262k | — |
| Nebius Token Factoryopennvidia/nemotron-3-super-120b-a12b | $0.3 | $0.9 | $0.06 | — | 262k | — |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | $0.57 | $1.44 | $0.114 | — | 66k | — |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144 | $0.57 | $1.44 | $0.114 | — | 262k | — |
| Crusoeopennvidia/NVIDIA-Nemotron-3-Super-120B-A12B | $0.3 | $2.4 | $0.15 | — | 262k | — |
| stepping stone AGopenNVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B | $2.38 | $5.95 | $0.357 | — | 131k | — |
| AIHubMixfreenemotron-3-super-120b-a12b-free | free | free | — | — | 262k | — |
Nemotron 3 Super 120B A12B price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 4 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kenari | $0.0971 → $0.0971 | $0.48 | −0% | |
| Kilo Gateway | $0.075 → $0.06 | $0.4 → $0.32 | −20% | |
| OpenRouter | $0.3 → $0.075 | $2.4 → $0.4 | −83.3% | |
| Kilo Gateway | $0.08 → $0.075 | $0.45 → $0.4 | −11.1% | |
| Eden AI | $0.085 → $0.075 | $0.4 | −11.8% | |
| OpenRouter | $0.08 → $0.3 | $0.45 → $2.4 | +433.3% | |
| OpenRouter | $0.3 → $0.08 | $2.4 → $0.45 | −81.3% | |
| Kenari | free → $0.0971 | free → $0.48 | — | |
| OpenRouter | $0.08 → $0.3 | $0.45 → $2.4 | +433.3% | |
| OpenRouter | $0.085 → $0.08 | $0.4 → $0.45 | +12.5% | |
| OpenRouter | $0.08 → $0.085 | $0.45 → $0.4 | −11.1% | |
| OpenRouter | $0.085 → $0.08 | $0.4 → $0.45 | +12.5% | |
| Kilo Gateway | $0.085 → $0.08 | $0.4 → $0.45 | +12.5% |
Nemotron 3 Super 120B A12B pricing FAQ
What is the cheapest Nemotron 3 Super 120B A12B API?
As of Nov 22, 2026, Kilo Gateway has the lowest Nemotron 3 Super 120B A12B output price at $0.32 per 1M tokens, and Kilo Gateway has the lowest input price at $0.06 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Nemotron 3 Super 120B A12B?
13 providers list Nemotron 3 Super 120B A12B on Sovyron; 14 of them sell it at a metered per-token price.
Is Nemotron 3 Super 120B A12B free?
One provider lists a free-tier offer: AIHubMix. Free tiers usually have rate limits.
What is the context window of Nemotron 3 Super 120B A12B?
Nemotron 3 Super 120B A12B supports a 262k-token context window and up to 262k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—