NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3 Ultra 550B

Added Jun 4, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.

  • Reasoning
  • Tools
  • Parallel tools
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.50
Output
$2.50

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
56 tokens
Longer than 5% of 465 models

Side by side

Compare models

Put Nvidia Nemotron 3 Ultra 550B next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryQwen3.5 27B TEEMiniMax M2.7GPT 5All 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

22.9

Better than 56% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    49.3

    Composite of the coding evaluations

    Better than 45% of 168 scored models

Agentic work

  • AutomationBench-AA

    3.0%

    Workflow automation, penalized for guardrail violations

    Better than 18% of 173 scored models

  • AutomationBench-AA tasks completed

    0.3%

    Workflows finished end to end without a guardrail violation

    Better than 19% of 173 scored models

  • AA-Briefcasev1.1

    876 Elo

    Agentic knowledge work, rated head to head

    Better than 37% of 166 scored models

  • GDPval-AAv2.1

    1,013 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 36% of 187 scored models

Document reasoning

  • GDP.pdf

    5.0%

    Professional reasoning over PDF documents, all-pass rate

    Better than 21% of 171 scored models

  • AA-LCRv1.1

    79.3%

    Reasoning across long documents

    Better than 73% of 309 scored models

  • MLCR-AA

    5.6%

    Long-context reasoning over medical records

    Better than 18% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    28.4%

    Expert-level questions across academic fields

    Better than 59% of 323 scored models

  • GPQA Diamond

    86.7%

    Graduate-level science questions

    Better than 67% of 291 scored models

  • IFBench

    81.4%

    Following precise output instructions

    Better than 98% of 215 scored models

Coding

  • Terminal-Benchv4.0

    0.5%

    Practical software engineering in a terminal

    Better than 30% of 171 scored models

  • SciCode

    40.3%

    Scientific computing in Python

    Better than 22% of 174 scored models

Legacy evaluations

  • Terminal-Bench Hard

    36.4%

    Earlier terminal task suite

    Better than 70% of 212 scored models

  • τ²-Bench Telecom

    83.3%

    Tool use in a customer-support simulation

    Better than 63% of 214 scored models

  • AA-LCR (unversioned)

    79.3%

    Long-context reasoning, earlier grading

    Better than 73% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
112.4 tok/s
Faster than 67% of 250 models
Time to first token
1.4 s
Quicker than 89% of 250 models
Prompt cache hits
10.3%
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.