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

Nemotron 3 Ultra

nemotron-3-ultra-550b-a55bby NVIDIA
Try in Chat

NVIDIA 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...

Context

262K

Max output

no data

Price per million tokens

$0.60in$0.20cached$3.60out

-5%

Released

Jun 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-ultra-550b-a55b" 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-ultra-550b-a55b" 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

Temperature0-2Top-p0-1Stop sequences

Tools & structure

ToolsParallel tool callsStructured output

Reasoning

Reasoningnone · low · medium · high · xhigh · maxDefaultmedium

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceAzure OpenAI docs

Benchmarks6
BenchmarkScoreSource
MMLU-ProHugging Face · Aug 202686.8%Hugging Face · Aug 2026
GPQA DiamondHugging Face · Aug 202687.9%Hugging Face · Aug 2026
SWE-bench VerifiedHugging Face · Aug 202669.5%Hugging Face · Aug 2026
Humanity's Last ExamHugging Face · Aug 202626.1%Hugging Face · Aug 2026
LMArena EloLMArena · Aug 20261445LMArena · Aug 2026
Terminal-BenchHugging Face · Aug 202653.9Hugging Face · Aug 2026
Providers serving this model5
Status
Azure Foundry via Experiential CloudexperientialFW-Nemotron-3-Ultra-NVFP4no datano data99.9%#2 / 3262Kno data$0.66$2.64cache$0.13nvfp4no dataactiveestimated
Fireworks via Experiential Cloudexperientialaccounts/fireworks/models/nemotron-3-ultra-nvfp4no datano data99.9%#1 / 3262Kno data$0.60$2.40cache$0.12nvfp4ZDRactiveestimated
OpenRouterexperiential60 tok/s900ms98.7%#3 / 3262Kno data$0.60$3.13cache$0.10-no dataactiveestimated
Fireworksaccounts/fireworks/models/nemotron-3-ultra-bf16no datano data99.9%-262Kno data$0.60≈$3.60≈cache$0.20≈bf16ZDRactiveestimated
Azure FoundryNemotron-3-Ultra-550B-A55B-BF16no datano data99.9%-262Kno datano datano datano databf16no dataactive-
Hugging Face