Skip to content
ShilpBot
AI Models

NVIDIA Nemotron 3.5 Lightning (Free): Specs, Limits and How to Use It

NVIDIA Nemotron 3.5 Lightning free: open mixture-of-experts model, text input, 1M context. Specs, limits, test prompts and how to try it.

By ShilpBot Team · Published · 3 min read

Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA with 3 billion active parameters out of 30 billion in total. Its listing says it is suited to high-throughput agentic workloads and specialised tasks.

The name reflects the intent: speed and low cost per call. Compared with NVIDIA's larger Nemotron models it is built to be run many times rather than to solve the hardest problems in one pass.

Specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

NVIDIA Nemotron 3.5 Lightning quick facts

DetailValue
DeveloperNVIDIA
Model IDnvidia/nemotron-3.5-lightning:free
Added to the catalogue2026-08-11
TypeOpen mixture-of-experts model
Parameters3B active / 30B total
Context windowabout 1M tokens (1,000,000)
Maximum output65,536 tokens
Input typestext
PriceFree (paid listing: $0.070 in / $0.20 out per 1M tokens)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: not listed; Reasoning: supported, effort not adjustable.

What NVIDIA Nemotron 3.5 Lightning is good for

  • High-volume agent steps, classification and tool routing.
  • Fast drafts that you will review or refine with a stronger model.
  • Cheap experiments with a 1M-token context window.

Limits of NVIDIA Nemotron 3.5 Lightning

  • With 3B active parameters it will usually trail larger models on difficult reasoning.
  • Structured output (JSON schema) is not listed, so validate any JSON it returns.
  • Text only. For images use a vision model such as Nemotron 3.5 Super VL.

How NVIDIA Nemotron 3.5 Lightning compares

  • NVIDIA Nemotron 3 Ultra: Both have a 1,000,000-token context window; both cap output at 65,536 tokens; it activates 3B parameters per token against 55B.
  • LiquidAI LFM3-1.7B: It has a larger context window (1,000,000 against 262,144 tokens); its output cap is 65,536 tokens against 8,192.
  • Recursive Flint: It has a larger context window (1,000,000 against 262,144 tokens); its output cap is 65,536 tokens against 235,929; it activates 3B parameters per token against 2.5B.

Calling NVIDIA Nemotron 3.5 Lightning from code

Use the model ID nvidia/nemotron-3.5-lightning:free with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3.5-lightning:free", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what NVIDIA Nemotron 3.5 Lightning can do

  1. Classify 20 support tickets into five categories and compare against your own labels.
  2. Use it as a first-pass filter that decides whether a request needs a bigger model.
  3. Ask it to summarise a long log file and check whether it caught the first error.

What NVIDIA Nemotron 3.5 Lightning costs

The free listing costs nothing, but the same model also has a paid listing at about $0.070 per million input tokens and $0.20 per million output tokens. As a rough guide, sending 1 million input tokens and receiving 100,000 output tokens would cost about $0.090 on the paid listing. Use the free tier to test, and move to the paid route if you need steadier availability. Free pricing is set by the provider and can change at any time, so check the model page before you plan around it.

Keep reading

All free models are compared in our free AI chat models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

How does Nemotron 3.5 Lightning differ from Nemotron 3 Ultra?

Lightning activates about 3B of 30B parameters and targets speed and throughput. Ultra activates about 55B of 550B and targets frontier-level reasoning and orchestration.

Is NVIDIA Nemotron 3.5 Lightning free, and what are its limits?

As of 2026-11-16 the catalogue lists it at zero price. About 1M tokens (1,000,000) context window, up to 65,536 output tokens, model ID nvidia/nemotron-3.5-lightning:free. Free use can be rate limited and providers may change it.

#NVIDIA Nemotron 3.5 Lightning#NVIDIA free model#free AI model#AI chat model#speed model#Kilo Gateway#OpenRouter