Models / NVIDIA
Nemotron 3 Ultra
by NVIDIA ·
nvidia/nemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
reasoningtool-usereleased 2026-06-04
Legal score · raw
-
not yet benchmarked
Context
262K
max output 183K
Input
$0.75
per 1M tokens
Output
$3
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.15
5.0x cheaper than uncached
Uncached input
$0.75
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.