Nemotron 3.5 Lightning 30B A3B

Name: Nemotron 3.5 Lightning 30B A3B
Price: 0.1 USD
Author: NVIDIA

Nemotronv3.5 Lightning 30B A3BCurrent

NVIDIA(enterprise)

Released August 11, 2026

API Docs Playground

OpenTools Scorenormalized /100

20.8

Valuescore / $M

OpenTools Score

Context1.0M tokens

Price (In / Out)$0.10/M / $0.95/M

Training CutoffMay 2026 post-training; September 2025 pre-training

CategoryLarge Language Model

Max Output32.8K tokens

About Nemotron 3.5 Lightning 30B A3B

Nemotron 3.5 Lightning is NVIDIA open-weight 30B-A3B reasoning model for fast, long-running agents. Its hybrid Mamba-2, mixture-of-experts, and attention architecture supports function calling, coding, tool use, long context, and efficient local or serverless deployment.

Capabilities

textreasoningcodingtool usefunction callinglong contextagenticlocal deploymentopen weights

Input Modalities

text

Output Modalities

text

Technical Details

API Identifier: nvidia/nemotron-3.5-lightning-30b-a3b
Category: Large Language Model
Context Window: 1,048,576 tokens
Max Output Tokens: 32,768 tokens

Benchmarks

Performance scores for Nemotron 3.5 Lightning 30B A3B across standard benchmarks.

Artificial Analysis Intelligence Index v4.1.1Artificial Analysis · Aug 2026

24%

Pricing

Token pricing for Nemotron 3.5 Lightning 30B A3B API usage.

Input Tokens

$0.10/M

per million tokens

Output Tokens

$0.95/M

per million tokens

Pricing Calculator

Input tokens/month

Output tokens/month

Input cost$0.10

Output cost$0.48

Estimated monthly cost$0.58

NVIDIA build lists serverless NIM pricing at $0.10 input and $0.95 output per million tokens. Self-hosted weights are also available; infrastructure costs vary.

Competing Models

Same pricing tier — direct alternatives to Nemotron 3.5 Lightning 30B A3B

Mid-Range

GLM 5.1 z-ai

40.1

$0.95/M / $3.15/MCompare

DeepSeek V3.2 Speciale deepseek

90.3

$0.40/M / $1.20/MCompare

MiniMax M2.7 minimax

70.1

$0.30/M / $1.20/MCompare

Trinity Large Thinking arcee-ai

$0.22/M / $0.85/MCompare

Hermes 4 405B nous-research

$1.00/M / $3.00/MCompare

Kimi K2 Thinking moonshot-ai

$0.60/M / $2.50/MCompare

MiMo-V2-Pro xiaomi

32.4

$1.00/M / $3.00/MCompare

WizardLM-2 8x22B microsoft

$0.62/M / $0.62/MCompare

Devstral 2 2512 mistral

$0.40/M / $2.00/MCompare

GLM 5 Turbo z-ai

$1.20/M / $4.00/MCompare

MiniMax M2.5 minimax

$0.12/M / $0.99/MCompare

Kimi K2 0905 moonshot-ai

$0.40/M / $2.00/MCompare

GLM 5 z-ai

$0.72/M / $2.30/MCompare

DeepSeek V3.1 Terminus deepseek

68.4

$0.21/M / $0.79/MCompare

MiniMax M2-her minimax

$0.30/M / $1.20/MCompare

Kimi K2 0711 moonshot-ai

$0.57/M / $2.30/MCompare

GLM-5.2 z-ai

27.3

$1.40/M / $4.40/MCompare

Gemini 3.5 Flash-Lite google

8.9

$0.30/M / $2.50/MCompare

Muse Spark 1.1 meta

23.9

$1.25/M / $4.25/MCompare

DeepSeek V4 Pro deepseek

52.7

$0.43/M / $0.87/MCompare

NVIDIAenterprise

The Engine of AI

2 Tools6 ModelsFounded 1993Santa Clara, California, United States

View full profile

2 Tools·6 Models

Tools by NVIDIA

Other AI tools from the same organization.

OpenShell

AI Infrastructure

OpenShell - Safe Runtime for Autonomous AI Agent Workflows

NeMo

Developer Tools

NeMo - NVIDIA Framework for Generative AI Builders

AI Models by NVIDIA

Large language models from the same organization.

Model	Context Window	Price (In / Out per M)	Capabilities
Nemotron 3 SuperCurrent	262K	-- / --	textcode
Nemotron 3 SuperCurrent	262K	$0.09 / $0.45	textcode
Nemotron 3 Nano 30B A3BCurrent	256K	-- / --	textcode
Nemotron 3 Nano 30B A3BCurrent	262K	$0.05 / $0.20	textcode
EagleCurrent	1	Free / Free	visionimage understandingmultimodalresearch