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

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...

At a glance

Context window: 1M tokens
Max output: 10M tokens
Knowledge to: —
Released: 2026

Pricing

Input: 1,999
Output: 1,999
Cached input: —
Cache write: —

IRR / 1M tokens · This model has no separate cache rate.

Capabilities

Input & output

Input: text

Output: text

Reasoning

SupportedLevels: high, medium

Tokenizer

Other

Benchmarks

Intelligence index: 38Coding index: 49

Source: Artificial Analysis

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.