F24 SALES Tested with real API requests

F24 SALES / MODEL

← Back to the directory

NVIDIA🇺🇸

Nemotron 3.5 Lightning

NVIDIA's compact reasoning model uses a sparse architecture with 30 billion total parameters and 3 billion active per token. Its design combines long-context processing with inference optimizations for applications where response time matters.

CONTEXT1M
MAX OUTPUT64K
LAST SCAN13 Nov 2026
🏆First observed free at Kilo, OpenRouter on .
Reasoning Open weights Text

Free aggregator routes

These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.

Limits above: Kilo. Available gateway routes are listed below.

Kilo
Info
Thinking
Supported
Model ID · Kilo APInvidia/nemotron-3.5-lightning:free
OpenRouter
Info
Thinking
Supported
Control
Can be toggled
Model ID · OpenRouter APInvidia/nemotron-3.5-lightning:free
Cline
Info
Thinking
Not advertised by this API
Model ID · Cline APInvidia/nemotron-3.5-lightning:free
NVIDIA
Info
Thinking
Not advertised by this API
Model ID · NVIDIA APInvidia/nemotron-3.5-lightning-30b-a3b
Context here
1M
Max output here
32K

Model sources

Use it through LiteLLM

Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.

Download LiteLLM YAML

Sources & references