Experiential
ModelsLogs
Star us on GitHubDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

Nemotron 3 Ultra

nemotron-3-ultra-550b-a55bby NVIDIAZDR (all rungs)Free

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...

Try in Playground

Context

512K

Max output

no data

Price per million tokens

$0.60$0in$0.20$0cached$3.60$0out

Waterfall

  1. Fireworks via Experiential Cloudfree tierFree$0.60/$3.6099.9% up--
  2. 1
    Fireworks via Experiential Cloud$0.60/$3.6099.9% up--

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-pr-136.preview.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
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-p0-1Top-kStop sequences

Tools & structure

ToolsParallel tool callsStructured output

Reasoning

Hugging Face

Fastest

60 tok/s

Released

Jun 2026

Promotion

FreeYour limits

Reasoningnone · low · medium · high · xhigh · maxDefaultmedium

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceFireworks 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 model2
Status
Azure Foundry via Experiential Cloudfree tierno datano data99.9%512Kno dataFreeFreeFreenvfp4no dataactiveestimated
Azure Foundry via Experiential Cloudexperientialno datano data99.9%512Kno data$0.60≈$3.60≈cache$0.20≈nvfp4no dataactiveestimated
Fireworks via Experiential Cloudexperientialno datano data99.9%512Kno data$0.60≈$3.60≈cache$0.20≈nvfp4ZDRactiveestimated