Atlas / Models / Nvidia / NVIDIA: Nemotron 3 Ultra

NVIDIA: Nemotron 3 Ultra✓ Catalog verified

nvidia/nemotron-3-ultra-550b-a55b

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...

Input price
$0.60 /1M
Output price
$3.60 /1M
Context
512K
Modalities
text
Released
Jun 4, 2026
Tool calling
✓ Yes
Atlas signal
88/100
01

Overview

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...

Access: available through the official Nvidia API. Context window: 512K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 6, 2026
02

Specifications

API identifiernvidia/nemotron-3-ultra-550b-a55b
ProviderNvidia
Model typeText LLM
Context window512K catalog
Input modalitiestext
Output modalitiestext
ReleasedJun 4, 2026
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_k": null,
  "top_p": 0.95,
  "temperature": 1,
  "presence_penalty": null,
  "frequency_penalty": null,
  "repetition_penalty": null
}
03

Pricing

Live pricing components for nvidia/nemotron-3-ultra-550b-a55b as published in the catalog.

$0.60
Input /1M
$3.60
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$6e-7$0.60 / 1MPer input token
Completion tokens$0.0000036$3.60 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$1.02Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

NVIDIA: Nemotron 3 Ultra
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call NVIDIA: Nemotron 3 Ultra through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does NVIDIA: Nemotron 3 Ultra cost?

$0.60 per 1M input tokens and $3.60 per 1M output tokens on the official Nvidia API.

What is the context window of NVIDIA: Nemotron 3 Ultra?

NVIDIA: Nemotron 3 Ultra supports up to 512K tokens of context.

Does NVIDIA: Nemotron 3 Ultra support tool / function calling?

Yes, NVIDIA: Nemotron 3 Ultra supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access NVIDIA: Nemotron 3 Ultra?

Use the official Nvidia API with the model id `nvidia/nemotron-3-ultra-550b-a55b`. See the Quick start section above for code examples.