Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. NVIDIA

Nvidia Nemotron 3.5 Lightning Thinking

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace.

  • Reasoning
  • Tool Calling
  • Parallel Tool Calls

Added Aug 12, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.05
Output
$0.20
Cache read
$0.01
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
30B / 3B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1351.6

Overall Rank

#225 / 426

Votes

25,030

Confidence Interval

1346.3 - 1357.0

Category Scores

Coding

#198 / 421

6,191 votes

1428.0

Math

#200 / 408

1,127 votes

1374.3

Longer Query

#233 / 404

10,788 votes

1347.8

Creative Writing

#271 / 424

5,465 votes

1283.7

Instruction Following

#223 / 426

8,443 votes

1343.4

Hard Prompts

#220 / 426

15,939 votes

1373.4

Additional Categories
22

French

#172 / 305

877 votes

1404.8

Japanese

#193 / 288

445 votes

1273.0

Expert

#195 / 374

2,602 votes

1394.5

Spanish

#195 / 307

820 votes

1368.0

Korean

#197 / 289

408 votes

1285.1

Industry Software And It Services

#201 / 426

9,283 votes

1411.3

English

#203 / 426

9,874 votes

1387.0

German

#205 / 321

441 votes

1322.9

Industry Mathematical

#205 / 405

1,330 votes

1373.4

Chinese

#206 / 399

1,947 votes

1389.9

Hard Prompts English

#206 / 424

6,351 votes

1401.5

Industry Business And Management And Financial Operations

#219 / 419

4,576 votes

1355.2

Polish

#219 / 243

407 votes

1294.3

Exclude Ties

#222 / 426

19,034 votes

1314.8

Multi Turn

#228 / 424

3,446 votes

1344.4

Non English

#238 / 426

15,154 votes

1320.1

Industry Life And Physical And Social Science

#240 / 424

4,113 votes

1358.5

Industry Legal And Government

#249 / 397

2,077 votes

1340.8

Industry Entertainment And Sports And Media

#253 / 424

6,311 votes

1293.7

Industry Medicine And Healthcare

#257 / 394

1,760 votes

1338.0

Industry Writing And Literature And Language

#263 / 425

6,897 votes

1304.0

Russian

#291 / 390

3,383 votes

1282.6

Published 2026-11-19 · Matched as NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4) · CC BY 4.0

LMArena Dataset

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.05$0.20$0.01N/AN/A
Auto
Auto (Anonymized)
$0.05$0.20$0.01N/AN/A
Darkbloom
Darkbloom
TEE attested
INT4
GLB
$0.021$0.101N/AN/AN/A
Fireworks
Fireworks
US
$0.0525$0.21$0.0105N/AN/A
DeepInfra
DeepInfra
BF16
US
$0.063$0.168$0.0315N/AN/A
CoreWeave
CoreWeave
BF16
US
$0.0735$0.21$0.042N/AN/A
ModelRun
ModelRun
FP4
US
$0.0735$0.21$0.042N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
ProviderInputOutputCached input
Auto
Autonvidia/nemotron-3.5-lightning:thinking
$0.05/M$0.20/M$0.01/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Nvidia Nemotron 3.5 Lightning Thinking with similar models from the same provider or model family.

Nvidia Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant.

Nvidia Nemotron 3.5 Super VL

nvidia/nemotron-3.5-super-vl

NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. A 262,144-token shared context window with responses limited to 16,384 tokens. OpenMDW 1.1 license.

Nemotron 3.5 Content Safety

nvidia/nemotron-3.5-content-safety

Nemotron 3.5 Content Safety is a content moderation classifier that labels user messages and assistant responses as safe or unsafe. It supports a 131,072-token context window and optional reasoning.

Nvidia Nemotron 3 Ultra 550B

nvidia/nemotron-3-ultra-550b-a55b

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.

Nvidia Nemotron 3 Ultra 550B Thinking

nvidia/nemotron-3-ultra-550b-a55b:thinking

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.

Nvidia Nemotron 3 Nano 30B

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

Nvidia's latest Nemotron 3 Nano model with 30B total parameters (3B active) using hybrid Mamba-Transformer MoE architecture. Features excellent throughput and strong reasoning capabilities.