TokenRate

Nemotron 3 Nano 30B A3B Pricing

Fast

NVIDIA · 262K tokens context

Nemotron 3 Nano 30B A3B from NVIDIA costs $0.050 per 1 million input tokens and $0.200 per 1 million output tokens as of July 2026 (live OpenRouter data). The model supports a 262,144-token context window (approximately 196,608 words) with a 228K-token maximum output. A typical 1,000-token request costs $0.0000 in input charges; a 10,000-token request costs $0.0005.

Nemotron 3 Nano 30B A3B pricing and capability summary
Input price$0.050 / 1M tokens
Output price$0.200 / 1M tokens
Output / input ratio4.0×
Context window262,144 tokens (~196,608 words)
Maximum output228,000 tokens
Cost per 1K tokens (input)$0.0000
TierFast
Last verified

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

Live pricing from OpenRouter

Input Price

$0.050

per 1 million tokens

Output Price

$0.200

per 1 million tokens

Context Window

262K tokens

max 228K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.0000666$0.00008
10-page document (2,500 words)3,333$0.000167$0.0002
1,000 lines of code5,000$0.00025$0.0003
100K token document100,000$0.005$0.006

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Extremely cheap at $0.050/1M input tokens
  • Large 262K-token context window
  • Low latency for high-throughput workloads

Limitations

  • Less capable than flagship models on complex reasoning
  • Quality and availability can vary by hosting provider

Best Use Cases

High-volume classification
Text extraction and summarization
Simple chat and Q&A
Cost-sensitive pipelines

Calculate Nemotron 3 Nano 30B A3B Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Nemotron 3 Nano 30B A3B costs — and compare across all models.

Open Calculator →

Nemotron 3 Nano 30B A3B — FAQ

Related Models

Related Guides