Nemotron 3.5 Lightning (free)
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model designed for high-throughput agentic workloads. It supports text-based input and output while offering built-in reasoning and tool-calling capabilities. The model is available for free and features a large context window of one million tokens.
Nemotron 3.5 Lightning (free) specs and pricing
- Provider: NVIDIA
- Released: August 11, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text
- Output: text
- Price: free
- Reasoning: yes
- Tool calling: yes
What Nemotron 3.5 Lightning (free) is good at
- High-throughput agentic workflows
- Complex reasoning tasks
- Applications requiring tool integration
To-dos to try with Nemotron 3.5 Lightning (free)
- Analyze a large technical document and extract specific action items
- Use tool calling to query an external database and summarize the findings
- Draft a multi-step project plan based on a provided set of requirements
FAQ
- Who developed Nemotron 3.5 Lightning? This model was developed by NVIDIA.
- What types of input does this model accept? Nemotron 3.5 Lightning is designed to process and generate text-based content.
- How much does Nemotron 3.5 Lightning (free) cost? Nemotron 3.5 Lightning (free) is available as a free model. In todo.is it doesn't use credits, though free models can be rate-limited by the provider.
- What is the context window of Nemotron 3.5 Lightning (free)? Nemotron 3.5 Lightning (free) can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Nemotron 3.5 Lightning (free) without coding? Yes. In todo.is you pick Nemotron 3.5 Lightning (free) as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.