NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3.5 Lightning Thinking

Added Aug 12, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

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
  • Tools
  • Parallel tools
Input
Text
Output
Text
Reasoning effort
none · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.20
Cache read
$0.01

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
6.1K tokens
Longer than 99% of 465 models

Side by side

Compare models

Put Nvidia Nemotron 3.5 Lightning Thinking next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGPT 5 NanoGLM 4.5DeepSeek R1 0528All 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

12.9

Better than 30% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    26.8

    Composite of the coding evaluations

    Better than 19% of 168 scored models

Agentic work

  • AutomationBench-AA

    0.8%

    Workflow automation, penalized for guardrail violations

    Better than 8% of 173 scored models

  • AutomationBench-AA tasks completed

    0.0%

    Workflows finished end to end without a guardrail violation

    Better than 0% of 173 scored models

  • AA-Briefcasev1.1

    506 Elo

    Agentic knowledge work, rated head to head

    Better than 21% of 166 scored models

  • GDPval-AAv2.1

    638 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 20% of 187 scored models

Document reasoning

  • GDP.pdf

    3.0%

    Professional reasoning over PDF documents, all-pass rate

    Better than 12% of 171 scored models

  • AA-LCRv1.1

    60.3%

    Reasoning across long documents

    Better than 37% of 309 scored models

  • MLCR-AA

    2.2%

    Long-context reasoning over medical records

    Better than 5% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    10.6%

    Expert-level questions across academic fields

    Better than 32% of 323 scored models

  • GPQA Diamond

    74.3%

    Graduate-level science questions

    Better than 33% of 291 scored models

Coding

  • Terminal-Benchv4.0

    0.5%

    Practical software engineering in a terminal

    Better than 30% of 171 scored models

  • SciCode

    32.1%

    Scientific computing in Python

    Better than 6% of 174 scored models

Legacy evaluations

  • AA-LCR (unversioned)

    60.3%

    Long-context reasoning, earlier grading

    Better than 37% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
About $0.05 per 1M input tokens with caching

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-lightning:thinking",
    "reasoning_effort": "none",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="nvidia/nemotron-3.5-lightning:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.