Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

Nemotron 3 Super

nemotron-3-super-120b-a12bby NVIDIA
Try in Chat

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Context

262K

Max output

16K

Price per million tokens

$0.085in$0.40out

-5%

Released

Mar 2026

Waterfall

No usable route yet. Experiential hosted routes appear automatically; connect a provider key below to use this model.

Quickstart

I want you to route my LLM calls for "nemotron-3-super-120b-a12b" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.jp/v1 as the base URL.
2. Securely ask me for my API key. Authenticate with my Experiential key from EXPLABS_API_KEY. I can create one under Settings -> API Keys.
3. Use the model id "nemotron-3-super-120b-a12b" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text

Sampling

Temperature0-1Top-p0-1

Tools & structure

ToolsStrict toolsStructured output

Streaming

Streaming

Sending an unsupported field? See error referenceBedrock docs

Benchmarks8
BenchmarkScoreSource
MMLU-ProHugging Face · Aug 202683.7%Hugging Face · Aug 2026
GPQA DiamondHugging Face · Aug 202679.2%Hugging Face · Aug 2026
SWE-bench VerifiedHugging Face · Aug 202660.5%Hugging Face · Aug 2026
AIME 2025Hugging Face · Aug 202690.2%Hugging Face · Aug 2026
AIME 2026Hugging Face · Aug 202690.0%Hugging Face · Aug 2026
Humanity's Last ExamHugging Face · Aug 202618.3%Hugging Face · Aug 2026
LMArena EloLMArena · Aug 20261378LMArena · Aug 2026
Terminal-BenchHugging Face · Aug 202631.0Hugging Face · Aug 2026
Providers serving this model7
Status
OpenRouterexperiential60 tok/s900ms98.1%#1 / 1262K16K$0.080$0.45$0.080-no dataactiveestimated
Azure FoundryFW-Nemotron-3-Super-120B-A12B-BF16no datano data99.9%-262K16K$0.085≈$0.40≈no data≈bf16no dataactiveestimated
Bedrock via Experiential Cloudno datano data99.9%-262K16K$0.15$0.65no data-ZDRdisabledestimated
Fireworksaccounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8no datano data99.9%-262K16K$0.085≈$0.40≈no data≈fp8ZDRactiveestimated
Fireworksaccounts/fireworks/models/nemotron-3-super-120b-a12b-bf16no datano data99.9%-262K16K$0.085≈$0.40≈no data≈bf16ZDRactiveestimated
Fireworksaccounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4no datano data99.9%-262K16K$0.085≈$0.40≈no data≈nvfp4ZDRactiveestimated
Azure FoundryNemotron-3-Super-120B-A12B-BF16no datano data99.9%-262K16Kno datano datano databf16no dataactive-
Hugging Face