Nemotron 3.5 Lightning 30B A3B

Nemotron 3.5 Lightning 30B A3B is a fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads. It is part of the Nemotron line, succeeding the Nemotron 3 Ultra 550B A55B released 2026-06-04. It has a context window of 262144 tokens and a max output of 262144 tokens. The weights are open. It supports reasoning mode and tool calling. It accepts text and returns text. The price is from $0.00 per million input tokens and $0.00 per million output tokens.

Against Nemotron 3 Ultra 550B A55B: window 1M to 262K, input $0.50 to $0.00, output $2.20 to $0.00.

• ·Fast MoE architecture for agentic tasks
• ·262k token context window
• ·262k token max output
• ·Open weights
• ·Supports reasoning and tool calling

• Reach for it for reliable agentic workflows
• Reach for it for enterprise workload automation
• Reach for it for long-context reasoning tasks
• Reach for it for tool-calling agents

3 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and max output?

The context window is 262144 tokens, and the max output is also 262144 tokens.

Are the weights open?

Yes, the weights are open.

What is the price?

The price is from $0.00 per million input tokens and $0.00 per million output tokens.