NVIDIA: Nemotron 3 Nano 30B A3B API Pricing
by nvidia · 262K context window ·
Explore NVIDIA Nemotron 3 Nano 30B A3B API pricing for your large language model projects. Understand the cost structure: $0.05000 per 1 million input tokens, $0.20000 per 1 million output tokens, and a total cost of $0.2500 per 1 million tokens. Nemotron 3 Nano 30B A3B features a context window of 262,144 tokens. Compare NVIDIA's offering with other LLM APIs. For example, processing 100 million tokens per day (80M input, 20M output) would cost approximately $16 per day, or $480 per month. Make informed decisions for cost-effective and powerful AI development with NVIDIA.
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | $0.01 |
| 1M tokens/month | $0.12 |
| 10M tokens/month | $1.25 |
| 100M tokens/month | $12.50 |
Compare with other models
NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-4o →NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-4o-mini →NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use NVIDIA: Nemotron 3 Nano 30B A3B when your quality requirements demand it.