Nemotron 3 Ultra model profile

Evidence snapshot: 2026-09-06

Nemotron 3 Ultra is a NVIDIA model profile with a 262,144-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.

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 supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks. It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Nemotron 3 Ultra is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Nemotron 3 Ultra is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.

Nemotron 3 Ultra accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.

The dated reference snapshot lists $0.5 input and $2.2 output per million tokens. Cached input is $0.1 per million tokens.

Nemotron 3 Ultra ranked #97 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Model research profile
Provider or publisher: NVIDIA
Context window: 262,144 tokens
Snapshot date: 2026-09-06
Knowledge cutoff: Not disclosed
Reference catalog ID: nvidia/nemotron-3-ultra-550b-a55b

When to pick Nemotron 3 Ultra

Nemotron 3 Ultra is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.

Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
Reach for it when you want to trade depth against cost per call. Reasoning effort is selectable across high, medium, so one route can serve both cheap and deep work.
Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.

Context, modalities, and identity

Nemotron 3 Ultra accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.

Provider or publisher: NVIDIA
Context window: 262,144 tokens
Maximum output: 32,768 tokens
Input modalities: text
Output modalities: text
Knowledge cutoff: Not disclosed

Model overview

Reference model ID: nvidia/nemotron-3-ultra-550b-a55b
Canonical version: nvidia/nemotron-3-ultra-550b-a55b-20260604
Hugging Face ID: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

prompt caching
reasoning controls
structured output
text generation
tool calling

Dated pricing snapshot

The dated reference snapshot lists $0.5 input and $2.2 output per million tokens. Cached input is $0.1 per million tokens.

These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.

Price date: 2026-09-06
Input: $0.5 per 1M tokens
Cached input: $0.1 per 1M tokens
Output: $2.2 per 1M tokens

Provider routes, performance, and uptime

The snapshot retains 4 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

Active provider endpoints: 4
Best p50 latency: 0.33 s
Best p50 throughput: 159 tok/s
Availability with routing: 99.99% over the sampled window
Availability without routing: 89.29% over the sampled window
Performance date: 2026-09-06

Provider	Quantization	Input / 1M	Output / 1M	Cache read / 1M	Context	p50 latency	p50 throughput	Uptime (1d)
DeepInfra	fp4	$0.5 / 1M	$2.2 / 1M	$0.1 / 1M	262,144 tokens	No recent p50	No recent p50	99.14%
Baseten (US)	fp4	$0.6 / 1M	$2.4 / 1M	$0.12 / 1M	202,800 tokens	0.41 s	131 tok/s	100.00%
Baseten	fp4	$0.6 / 1M	$2.4 / 1M	$0.12 / 1M	202,800 tokens	0.33 s	159 tok/s	100.00%
Venice	fp8	$0.625 / 1M	$3.125 / 1M	$0.1875 / 1M	256,000 tokens	8.60 s	21 tok/s	99.88%

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Coding Index: 49.3
Agentic Index: 21.7

Design Arena category	Elo	Win rate	Rank
3d	1171	41%	#59
asciiart	1099	36.4%	#55
codecategories	1153	36.3%	#77
dataviz	1159	38.3%	#70
gamedev	1156	37%	#70
svg	1113	36.2%	#58
uicomponent	1158	37.4%	#70
website	1142	34.3%	#82

Popularity and market context

Third-party catalog rank: #97
Global market share: Not inferred
Observation date: 2026-09-06

Frequently asked questions

When should I use Nemotron 3 Ultra?

Nemotron 3 Ultra is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Reach for it when you want to trade depth against cost per call: Reasoning effort is selectable across high, medium, so one route can serve both cheap and deep work. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.

What is Nemotron 3 Ultra?

What context window does Nemotron 3 Ultra have?

The dated profile lists 262,144 tokens of context and up to 32,768 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for Nemotron 3 Ultra?

The 2026-09-06 snapshot includes 2 Artificial Analysis indexes and 8 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Is Nemotron 3 Ultra available through Kendr?

This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.

Does the popularity rank represent Nemotron 3 Ultra's global market share?

Sources and evidence dates

Nemotron 3 Ultra third-party catalog record (catalog, checked 2026-09-06)
Third-party model catalog methodology (methodology, checked 2026-09-06)
NVIDIA official model documentation (primary, checked 2026-09-06)
Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)