computetrail

All models ·nvidia

NVIDIA: Nemotron 3 Nano 30B A3B

Provider: nvidia · nvidia/nemotron-3-nano-30b-a3b

Input
$0.05 /1M
Output
$0.2 /1M
Cache read
$0.03 /1M
Context
262,144 tokens

How NVIDIA: Nemotron 3 Nano 30B A3B pricing compares

At $0.2 / 1M output tokens, NVIDIA: Nemotron 3 Nano 30B A3B is the 2nd-cheapest of 5 nvidia models we track. It's cheaper than 92% of the 392 paid models on computetrail (34th-cheapest overall). Output costs 4.0× its input price ($0.05 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.09 / 1M blended. Reading cached input costs 40% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 262,144 tokens context window ranks 203rd-largest of 392 models with a published limit.

Output price history

$0.200$0.20006-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has held steady at $0.2 / 1M — no change so far.

Similar-priced models

ModelProviderOutput $/1MContext
NVIDIA: Nemotron 3.5 Lightningnvidia$0.2262,144
Mistral: Mistral Small 3.2 24Bmistralai$0.2131,072
Meta: Llama 3.2 1B Instructmeta-llama$0.20160,000
Qwen: Qwen3 14Bqwen$0.24131,072
Amazon: Nova Lite 1.0amazon$0.24300,000
DeepSeek: DeepSeek V4 Flash 0423deepseek$0.1591,048,576

Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.