N

NVIDIA: nemotron-3-nano-30b-a3b:free

nemotron-3-nano-30b-a3b:free
262.1K context262.1K outReasoningToolsCacheStructured
Released Dec 14, 2025Updated Jun 18, 2026

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Tokenizer OtherQuantization fp4nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 262.1K tokensCompatible endpoints openaiVendor NVIDIA

Uptime

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providersNot sent by default
include_reasoningAll providers-
logit_biasAll providers-
logprobsSome providers-
max_tokensAll providers-
min_pAll providers-
presence_penaltyAll providers-
reasoningAll providers-
repetition_penaltyAll providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsSome providers-
temperatureAll providersNot sent by default
tool_choiceAll providers-
toolsAll providers-
top_kAll providers-
top_logprobsSome providers-
top_pAll providersNot sent by default

Frequently asked questions

Similar models