Enterprise DNAEnterprise DNA
NVIDIA logo

Models · Long context

Nemotron 3 Ultra

by NVIDIA

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Visit NVIDIA ↗

Our verdict

Not reviewed yet

We have not reviewed Nemotron 3 Ultra yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Notes

Nemotron 3 Ultra is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.600 per million tokens
Checked OpenRouter models API
Output price
$2.40 per million tokens
Checked OpenRouter models API
Price on baseten
$0.120 per million cached input tokens
Checked OpenRouter models API
Price on baseten
$0.600 per million input tokens
Checked OpenRouter models API
Price on baseten
$2.40 per million output tokens
Checked OpenRouter models API
Price on deepinfra
$0.080 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.400 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$1.76 per million output tokens
Checked OpenRouter models API
Price on venice
$0.188 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
85.4% (for 4 June 2026)
Checked Epoch AI (CC BY 4.0)
Apex agents
22.7% (for 4 June 2026)
Checked Epoch AI (CC BY 4.0)
Dtbench
90.1% (for 4 June 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `nvidia/nemotron-3-ultra-550b-a55b`.

  • openrouter · nvidia/nemotron-3-ultra-550b-a55b · Docs

OpenRouter id: nvidia/nemotron-3-ultra-550b-a55b

Price

What Nemotron 3 Ultra costs, over time

Input price

$0.600 to $0.600

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$2.40 to $2.40

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
basetenCached input$0.120 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenOutput$2.40 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.080 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.400 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$1.76 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceCached input$0.188 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.625 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$3.13 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Nemotron 3 Ultra is used

Tokens served a day

797.3B to 579.2B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Nemotron 3 Ultra scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index11.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index49.3indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index20.1indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)1,143EloAs of 10 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)22.7percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)90.1percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)13.6percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)85.4percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)36.9percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)20percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated86.7percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)2percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Show 1 more score
ScoreValueSourceChecked
Weirdml (best-across-versions)43.5percentAs of 4 June 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 2.2 to 2.4

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.5 to 0.6

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 2.4 to 2.2

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.6 to 0.5

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 3.125 to 2.4

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.625 to 0.6

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 2.4 to 3.125

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.6 to 0.625

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 3.6 to 2.4

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 2.2 to 3.6

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.5 to 0.6

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Nemotron 3 Ultra is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
3.3T ▲9.1%
Requests, last 7 days
41.3M
Tool calls, last 7 days
20.4M
Intelligence score
11.8
Average cost per request
48.2¢
Price per million tokens
$0.6 in · $2.4 out
01T2T19 Sept: 797B tokens, 5.7M requests20 Sept: 783B tokens, 5.7M requests21 Sept: 748B tokens, 5.7M requests22 Sept: 754B tokens, 5.8M requests23 Sept: 486B tokens, 4.3M requests24 Sept: 630B tokens, 5.5M requests25 Sept: 989B tokens, 7.5M requests26 Sept: 1.1T tokens, 7.9M requests27 Sept: 1T tokens, 7.9M requests28 Sept: 967B tokens, 8.3M requests29 Sept: 716B tokens, 6.5M requests30 Sept: 693B tokens, 6.2M requests1 Oct: 760B tokens, 6.1M requests2 Oct: 786B tokens, 6.3M requests3 Oct: 836B tokens, 6.4M requests4 Oct: 918B tokens, 6.9M requests5 Oct: 849B tokens, 6.9M requests6 Oct: 862B tokens, 6.9M requests7 Oct: 962B tokens, 7.7M requests8 Oct: 974B tokens, 7.6M requests9 Oct: 1T tokens, 8M requests10 Oct: 1.1T tokens, 8.5M requests11 Oct: 1.2T tokens, 8.9M requests12 Oct: 1.1T tokens, 8.6M requests13 Oct: 1.1T tokens, 8.7M requests14 Oct: 1T tokens, 8.2M requests15 Oct: 780B tokens, 6.6M requests16 Oct: 87.4B tokens, 1.2M requests17 Oct: 72.8B tokens, 893K requests18 Oct: 792B tokens, 5.5M requests19 Oct: 813B tokens, 6M requests20 Oct: 945B tokens, 7M requests21 Oct: 1T tokens, 7.5M requests22 Oct: 948B tokens, 7.3M requests23 Oct: 888B tokens, 7.4M requests24 Oct: 634B tokens, 6.2M requests25 Oct: 666B tokens, 6.1M requests26 Oct: 445B tokens, 5.3M requests27 Oct: 451B tokens, 5.5M requests28 Oct: 458B tokens, 5.3M requests29 Oct: 422B tokens, 4.9M requests30 Oct: 418B tokens, 5M requests31 Oct: 441B tokens, 5.2M requests1 Nov: 394B tokens, 4.9M requests2 Nov: 368B tokens, 4.8M requests3 Nov: 498B tokens, 5.9M requests4 Nov: 431B tokens, 5.4M requests5 Nov: 402B tokens, 5M requests6 Nov: 409B tokens, 5.1M requests7 Nov: 460B tokens, 5.4M requests8 Nov: 463B tokens, 6.4M requests9 Nov: 529B tokens, 6.8M requests10 Nov: 579B tokens, 7.2M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Nemotron 3 Ultra.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-11. Hosting routes and app features can differ.

DeveloperNVIDIA
Exact model identifiernvidia/nemotron-3-ultra-550b-a55b
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
openmdw-1.1, open weights
Context length
262K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
4 Jun 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

nvidia/nemotron-3-ultra-550b-a55b: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-11
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-11
Licence source ↗

Licence declared in the nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 11.8 (2026-11-09) ↗Coding Index: 49.3 (2026-11-09) ↗Agentic Index: 20.1 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →