Capabilities
7-day heat trend
−23.9%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 80% of tracked models
- Faster than 51% of tracked models
- Efficiency rank: #4 of 120
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About Nemotron 3 Super
Nemotron 3 Super is a Text model from NVIDIA (US). HotON.ai tracks it at $0.09 per 1M input tokens and $0.45 per 1M output tokens, with a 1000K-token context window, ~152 tokens/sec throughput and 96.5% availability. Its composite efficiency score is 96/100 at an estimated $0.000 per successful task.
Compare Nemotron 3 Super
Related market news
Frequently asked questions
How much does Nemotron 3 Super cost per 1M tokens?+
Nemotron 3 Super is tracked at $0.09 per 1M input tokens and $0.45 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.36 per 1M tokens. Figures are illustrative demo data.
What is Nemotron 3 Super best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is Nemotron 3 Super?+
Nemotron 3 Super delivers about 152 tokens/sec with 96.5% tracked availability, suitable for latency-sensitive, real-time applications.
Is Nemotron 3 Super cheaper than other AI models?+
Within the HotON.ai tracked set, Nemotron 3 Super is cheaper than 80% of models on input price and ranks #4 of 120 by overall efficiency.
Related models
Pricing and availability are real (via OpenRouter, updated daily — availability is the best-serving provider's 24h uptime). Efficiency is a HotON composite of real price and context. Speed is a modeled estimate.