Nemotron 3 Ultra API

NVIDIA Nemotron 3 Ultra is a reasoning and orchestration model built on a hybrid Transformer-Mamba Mixture-of-Experts architecture, optimized for complex reasoning, long-context analysis, and agent workflows with up to 1M context length.

Modalities: TextText
In / Out price: $0.6348/$3.81per 1M
Context window: 1M tokens
Released: Jun 4, 2026

Nemotron 3 Ultra overview

Nemotron 3 Ultra by NVIDIA

Optimized for complex multi-step reasoning, long-context analysis, and agentic workflows. Supports tool use and extended context up to 1M tokens.

Nemotron 3 Ultra specs

Model ID: nvidia/nemotron-3-ultra-550b-a55b
Developer: NVIDIA
Context window: 1,000,000 tokens
Max output: 32,768 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

NVIDIA Nemotron 3 Ultra is a next-generation reasoning and orchestration model based on a hybrid Transformer-Mamba Mixture-of-Experts architecture with 550 billion total parameters and 55 billion active parameters per forward pass. Designed for enterprise-grade agentic workflows, it delivers strong performance on complex reasoning tasks, multi-step analysis, and long-document understanding, with support for contexts up to 1 million tokens.

Performance Benchmarks

550B total parameters, 55B active per forward pass (MoE architecture).
Context window: up to 1,000,000 tokens.
Strong performance on reasoning, coding, and instruction-following benchmarks.
Optimized for multi-step and chain-of-thought reasoning scenarios.
Suitable for both interactive chat and batch inference workloads.

Architecture Breakdown

Nemotron 3 Ultra uses a hybrid Transformer-Mamba architecture combined with Mixture-of-Experts (MoE) routing. The MoE design activates only 55B of 550B parameters per token, enabling efficient inference at scale. The Mamba layers provide linear-complexity sequence modeling for long-context tasks, while Transformer attention layers handle high-precision reasoning over complex inputs.

Comparison with Other Models

VS DeepSeek R1: Nemotron 3 Ultra offers a 1M token context window vs. DeepSeek R1's shorter context; both target advanced reasoning but Nemotron uses a hybrid MoE architecture optimized for enterprise deployment.
VS Claude Sonnet 4: Claude Sonnet 4 focuses on balanced performance and speed; Nemotron 3 Ultra prioritizes extended context and MoE-driven reasoning efficiency at scale.
VS GPT-4o: GPT-4o delivers multimodal capabilities; Nemotron 3 Ultra specializes in long-context text reasoning and agentic orchestration with a larger parameter footprint.

Use cases

Customer service automation is a documented use case for Nemotron 3 Ultra 550B A55B, which NVIDIA describes as ideal for multi-agent enterprise workflows requiring highest accuracy.

Supply chain management is another documented use case, listed alongside customer service automation among the model’s enterprise workflow applications.

IT security is also explicitly named as a use case for the model in NVIDIA’s Nemotron overview, again in the context of high-accuracy multi-agent enterprise workflows.

The model is also described as suitable for deep research and complex reasoning tasks, including orchestration across coding and enterprise workflows.

Capabilities

Function calling
Streaming
Structured outputs

Nemotron 3 Ultra benchmarks by Artificial Analysis

See how Nemotron 3 Ultra compares in intelligence, generation speed, cost per task and latency. Data retrieved Nov 3, 2026.

Intelligence#41 / 5011.8Index v5.0 Speed#55 / 219161Output tokens / second Cost per task#29 / 44$2.23USD / benchmark task Latency#94 / 2161.21Seconds to first token

Intelligence

Index v5.0

Speed

Output tokens / second

Cost per task

USD / benchmark task

Benchmark results

Compare 6 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Nemotron 3 Ultra API pricing

Nemotron 3 Ultra pricing in US dollars
Usage	Price	Unit
Input	$0.6348	1M tokens
Output	$3.81	1M tokens
Cached input	$0.1587	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Nemotron 3 Ultra vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Nemotron 3 Ultra	$0.6348	$3.81
Nemotron 3.5 Content Safety	$0.2116	$0.2116
Nemotron 3 Nano 30B A3B	$0.0529	$0.2116
Nemotron 3 Super 120B-A12B	$0.0952	$0.4761
Nemotron 3.5 Super VL	$0.2645	$1.59

How to use the Nemotron 3 Ultra API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "nvidia/nemotron-3-ultra-550b-a55b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Nemotron 3 Ultra FAQ

What is the context window of Nemotron 3 Ultra?

Nemotron 3 Ultra has a 1,000,000 tokens context window and can return up to 32,768 tokens.

What inputs and outputs does Nemotron 3 Ultra support?

Nemotron 3 Ultra takes text as input and returns text.

What is the model ID for Nemotron 3 Ultra?

Use nvidia/nemotron-3-ultra-550b-a55b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Nemotron 3 Ultra released?

Nemotron 3 Ultra became available on June 4, 2026.

How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra costs $0.6348 input and $3.81 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Nemotron 3 Ultra support streaming?

Yes, Nemotron 3 Ultra can stream responses as they are generated.

Who created Nemotron 3 Ultra?

Nemotron 3 Ultra was built by NVIDIA.

Can Nemotron 3 Ultra call functions or use external tools?

Yes. It supports function calling, tools, and parallel tool calls.

Start building with Nemotron 3 Ultra

Get API key

Nemotron 3 Ultra API

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

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "nvidia/nemotron-3-ultra-550b-a55b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Nemotron 3 Ultra API

Nemotron 3 Ultra overview

Nemotron 3 Ultra by NVIDIA

Nemotron 3 Ultra specs

Performance Benchmarks

Architecture Breakdown

Comparison with Other Models

Use cases

Capabilities

Nemotron 3 Ultra benchmarks by Artificial Analysis

Intelligence

Speed

Cost per task

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Nemotron 3 Ultra API pricing

Nemotron 3 Ultra vs other models: token prices

How to use the Nemotron 3 Ultra API

Build with your agent

1Get your API key

2Make your first request

Related articles

Nemotron 3 Ultra FAQ

Start building with Nemotron 3 Ultra

Nemotron 3 Ultra API

Build with your agent

1Get your API key

2Make your first request

Nemotron 3 Ultra API

Nemotron 3 Ultra overview

Nemotron 3 Ultra by NVIDIA

Nemotron 3 Ultra specs

Performance Benchmarks

Architecture Breakdown

Comparison with Other Models

Use cases

Capabilities

Intelligence

Speed

Cost per task

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Nemotron 3 Ultra API pricing

Nemotron 3 Ultra vs other models: token prices

How to use the Nemotron 3 Ultra API

Build with your agent

1Get your API key

2Make your first request

Models similar to Nemotron 3 Ultra

Nemotron 3.5 Super VL

Nemotron 3.5 Lightning

Nemotron 3.5 Content Safety

Glimpse

Palmyra X5

Kimi K2 Thinking

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Nemotron 3 Ultra FAQ

Start building with Nemotron 3 Ultra