Skip to main content
AI HQ

NVIDIA

NVIDIA: Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b

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...

Listed (14 Dec 2025)

Source: OpenRouter (live)

Input
$0.060
USD per 1M tokens
Output
$0.240
USD per 1M tokens
Blended
$0.105
75% in / 25% out
Context
262K
tokens
Max output
236K
tokens
Modality
text->text

Prices as listed on OpenRouter, refreshed every five minutes. Provider-direct prices may differ. Convert to your currency on the AI Tracker.

Capabilities

Declared on the listing

  • Tool / function calling Declared
  • Reasoning controls Declared
  • Structured output Declared
  • InputText
  • OutputText

Capabilities are read from the provider listing. “Not declared” means the listing does not advertise the feature, not that it is absent.

Why it costs this

Pricing context

  • 87% below median
  • Cheap input
  • Cheap output
  • Market median blended price is $0.806/M across 417 priced models.

Alternatives

More from NVIDIA

More →
  1. $0.103

    /M blended

  2. $0.200

    /M blended

  3. $1.05

    /M blended

  4. $0.172

    /M blended

Alternatives

Similar price, other providers

More →
  1. $0.105

    /M blended

  2. $0.107

    /M blended

  3. Reka Edge

    Rekaai

    $0.100

    /M blended

  4. $0.100

    /M blended

  5. Qwen: Qwen3.5-9B

    Qwen (Alibaba)

    $0.112

    /M blended

  6. $0.113

    /M blended

Within ±50% of $0.105/M blended.

Nemotron open models. All NVIDIA models · Official site

Newsletter

Stay Ahead of AI

Get the most important developments in artificial intelligence delivered directly to your inbox.

No hype. No spam.

Just trusted insights, major model releases, pricing updates, benchmark changes, product reviews, and practical guidance from across the AI ecosystem.

  • Weekly AI Briefing
  • Major Model Releases
  • Pricing & Benchmark Updates
  • Unsubscribe Anytime

The AI HQ Briefing

One email a week. Read in five minutes.

By subscribing you agree to receive the AI HQ newsletter. Your address is processed by our email delivery provider and never sold. Unsubscribe anytime.