IranRouter
All models
NVIDIA

NVIDIA: Nemotron 3 Ultra

Unavailable

by NVIDIA

nvidia/nemotron-3-ultra-550b-a55bUsage rank #9

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...

At a glance

Context window
262Ktokens
Max output
183Ktokens
Knowledge to
Released
2026

Capabilities

CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupportedhighmedium

Benchmarks

Intelligence index
23
Coding index
49
Agentic index
22

Design Arena

CategoryEloWin rate
models · 3d1,16340.5
models · dataviz1,15638.4
models · codecategories1,15536.3
models · gamedev1,15536.9
models · uicomponent1,15137.2
models · website1,14534.5
models · svg1,09935.5
models · asciiart1,09736.5

Standard evaluations

BenchmarkScoreTasks
gpqa_diamond0.82579
tau_bench_verified_airline0.77150

Source: Artificial Analysis, Design Arena · as of Sep 16, 2026

Performance

Uptime on IranRouter

4.9%

Aug 18Sep 16

Reference uptime

100%

Aug 18Sep 16

Median latency

5,232 ms

Aug 18Sep 16

Throughput

75.1 tok/s

Aug 18Sep 16

IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.

Popularity

Current rank
#9
Rank change, 7 days
0

Daily tokens · 90 days

386.1B

Jun 18Sep 15

Ranked by daily token volume across the global model market; the figure above the chart is the daily average.

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Parameters this model accepts; anything else is ignored.

Quick start

from openai import OpenAI

client = OpenAI(
    api_key="ir-...",
    base_url="https://iranrouter.com/v1",
)

resp = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)

Only base_url and the key change; the rest of your code stays as it is.