AiCostCompare

Nemotron 3 Nano 30B A3B

by NVIDIA · nvidia/nemotron-3-nano-30b-a3b · #51 cheapest of 457 paid models

Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly

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. The model is fully...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.06

per 1M tokens

Output

$0.24

per 1M tokens

Blended (3:1)

$0.105

3 input : 1 output

Cache read

$0.012

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for Nemotron 3 Nano 30B A3B with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.105$0.00636—
50%$0.087$0.00396−38%
90%$0.073$0.00204−68%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000102$0.102
Document summary8,0001,000$0.00072$0.72
Codebase question (RAG)30,0002,000$0.00228$2.28
Long-context analysis150,0005,000$0.0102$10.20

Performance

Intelligence Index

—

AA composite quality

Coding Index

14.4

Math Index

—

Agentic Index

1

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Specs

Context window

262K

tokens

Max output

236K

tokens

Input modalities

text

Tokenizer

Other