F24 SALES Tested with real API requests

F24 SALES / MODEL

← Back to the directory

NVIDIA🇺🇸

Nemotron 3 Super

NVIDIA's 120-billion-parameter reasoning model activates 12 billion parameters per token. It is designed for conversational assistants and cooperating agents, including workflows that classify requests, plan actions and pass work between tools.

CONTEXT256K
MAX OUTPUT236K
LAST SCAN27 Oct 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-super-120b-a12b:free
OpenRouter
Info
Thinking
Supported
Effort levels
medium · low · none
Control
Can be toggled
Default
Enabled
Default effort
medium
Token budget
Supported
Model ID · OpenRouter APInvidia/nemotron-3-super-120b-a12b:free
Cline
Info
Thinking
Not documented
Model ID · Cline APInvidia/nemotron-3-super-120b-a12b:free
Context here
Not documented
Max output here
Not documented

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