Modeldex
Drag to turnCard front showing

NVIDIATextCommon

Nemotron 3.5 Lightning 30B A3B

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

nvidia/nemotron-3.5-lightning-30b-a3b
Type
Text
Quality
Not rated yet
Context window
262,144 tokens
Max output
262,144 tokens
Input price
Free
Output price
Free
Cache read
—
Cache write
—
Released
Aug 11, 2026
Knowledge cutoff
—
Takes in
Text
Puts out
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
File attachments
No
Access
Free
License
NVIDIA Open Model license
Rarity
Common
Set number
975/1040
Open NVIDIA docsWhere to run it 10Evolution 2/2Meet its creatureBattle North Small Translate

No matching Hugging Face repo was found, so this shows NVIDIA’s usual open-weight license. Check the model card before relying on it. Specs from models.dev, last changed Oct 18, 2026. Official source: docs.api.nvidia.com.

How good is it?

Public leaderboard scores for Nemotron 3.5 Lightning 30B A3B, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Nemotron 3.5 Lightning 30B A3B yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

10 providers sell Nemotron 3.5 Lightning 30B A3B through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
AIHubMixFreenemotron-3.5-lightning-freeFreeFree262K
Merge GatewayFreenvidia/nemotron-3.5-lightning-30b-a3bFreeFree1M
NvidiaOfficialFreenvidia/nemotron-3.5-lightning-30b-a3bFreeFree262K
RequestyFreenemotron-3.5-lightning-30b-a3bFreeFree1.05M
Kilo GatewayCheapest paidnvidia/nemotron-3.5-lightning$0.025$0.12262K
RunInfranvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16$0.05$0.15262K
Fireworks AIaccounts/fireworks/models/nemotron-lightning-3p5-30b-a3b$0.05$0.20262K
OpenRouternvidia/nemotron-3.5-lightning$0.07$0.20262K
Nebius Token Factorynvidia/Nemotron-3_5-Lightning$0.06$0.241.05M
Pioneernvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16$0.50$0.508K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

More from NVIDIA

NVIDIA

Nemotron 3.5 Super VL 120B A12B

CTX1.05M
New
Reasoning · Vision · Tools
TextImageVideoInputFree
TextOutputFree

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

FreeNVIDIA Open Model license1037/1040
NVIDIA

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

SIZE32B
Text
TextDownloads32K/mo
TextLikes25

Language model from NVIDIA, 32B parameters.

Open weightsOpenMDW 1.1 license965/1040
NVIDIA

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

SIZE32B
Text
TextDownloads690K/mo
TextLikes240

Language model from NVIDIA, 32B parameters.

Open weightsOpenMDW 1.1 license960/1040
NVIDIA

Nemotron-3-Embed-8B-BF16

SIZE8B
Embedding
TextDownloads110K/mo
–Likes110

Sentence embedding model from NVIDIA, 8B parameters.

Open weightsOpenMDW 1.1 license948/1040
NVIDIA

Nemotron-3-Embed-1B-BF16

SIZE1.1B
Embedding
TextDownloads220K/mo
–Likes170

Sentence embedding model from NVIDIA, 1.1B parameters.

Open weightsOpenMDW 1.1 license947/1040
NVIDIA

NVIDIA-Nemotron-Parse-2.0

SIZE903M
Vision
TextImageDownloads19K/mo
TextLikes120

Vision-language model from NVIDIA, 903M parameters.

Open weightsOpenMDW 1.1 license938/1040
NVIDIA

Nemotron 3.5 Content Safety

CTX128K
Safety · Vision
TextImageInputFree
TextOutput—

Safety model for policy screening, moderation, and risk-aware routing workflows

FreeOpenMDW License Agreement916/1040
NVIDIA

Nemotron 3 Ultra 550B A55B

CTX1M
Reasoning · Tools
TextInput$0.50/M
TextOutput$2.50/M

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Open weightsNVIDIA Open Model license915/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot