Nemotron 3 Ultra

Chat Completions

nemotron-3-ultra-550b-a55b

Nvidia|Created Jun 4, 2026|512.3k context

Chat Completions

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 supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Endpoints and request shape

This page collects the public integration surface for the model: supported endpoints, available request parameters, and example calls through the NagaAI API.

Chat Completions

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="nemotron-3-ultra-550b-a55b",
    messages=[
        {"role": "user", "content": "What's 2+2?"}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)

Supported Parameters

Available parameters for API requests

Frequency PenaltyLogprobsMax Completion TokensPresence PenaltyResponse FormatReasoning EffortStopTemperatureTool ChoiceToolsTop PParallel Tool CallsPredictionLogit Bias