NVIDIA: Nemotron Nano 9B V2 API Pricing
by nvidia · 131K context window ·
Explore NVIDIA Nemotron Nano 9B V2 API pricing for large language model applications. Understand the cost structure with a clear breakdown: input tokens are priced at $0.04000 per 1 million tokens, output tokens at $0.16000 per 1 million tokens, and the all-in cost is $0.2000 per million tokens. Nemotron Nano 9B V2 offers a context length of 131,072 tokens. For example, processing 50 million tokens monthly (input and output combined) would cost approximately $10. This page provides essential pricing details for ML engineers evaluating LLM APIs and considering NVIDIA's offering for their projects. Make informed decisions about your AI infrastructure with accurate cost estimations.
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | $0.01 |
| 1M tokens/month | $0.10 |
| 10M tokens/month | $1.00 |
| 100M tokens/month | $10.00 |
Compare with other models
NVIDIA: Nemotron Nano 9B V2 vs OpenAI: GPT-4o →NVIDIA: Nemotron Nano 9B V2 vs OpenAI: GPT-4o-mini →NVIDIA: Nemotron Nano 9B V2 vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use NVIDIA: Nemotron Nano 9B V2 when your quality requirements demand it.