NVIDIA: nemotron-3-ultra-550b-a55b:free

nemotron-3-ultra-550b-a55b:free
131.1K context16.4K outToolsCacheStructured
Released Jun 4, 2026Updated Jun 4, 2026

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 131.1K tokensCompatible endpoints openaiVendor NVIDIA

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-
max_tokensAll providers-
min_pSome providers-
presence_penaltyAll providersNot sent by default
reasoningAll providers-
repetition_penaltyAll providersNot sent by default
response_formatAll providers-
seedSome providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers1
tool_choiceAll providers-
toolsAll providers-
top_kAll providersNot sent by default
top_pAll providers0.95

Frequently asked questions

Similar models