You're looking at a specific version of this model. Jump to the model overview.

nvidia /nemotron-3-nano-30b-a3b:135b4a9c

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
Input prompt for the model
system_prompt
string
System prompt to guide model behavior (optional)
max_new_tokens
integer
256

Min: 1

Max: 8192

Maximum number of tokens to generate
temperature
number
1

Max: 2

Temperature for sampling. Use 1.0 for reasoning tasks, 0.6 for tool calling
top_p
number
1

Max: 1

Top-p (nucleus) sampling. Use 1.0 for reasoning tasks, 0.95 for tool calling
top_k
integer
50

Max: 100

Top-k sampling. Lower values make output more focused
repetition_penalty
number
1.1

Min: 1

Max: 2

Penalty for repeating tokens. Higher values reduce repetition
enable_thinking
boolean
True
Enable reasoning/thinking mode for complex problems. Set to False for greedy search

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'items': {'type': 'string'},
 'title': 'Output',
 'type': 'array',
 'x-cog-array-display': 'concatenate',
 'x-cog-array-type': 'iterator'}