LLM Pricing

← All Models

NVIDIA: Nemotron 3 Ultra

🇺🇸 NVIDIA · Nemotron 3

Input Price $0.600 per million tokens NT$19.2
Output Price $2.40 per million tokens NT$76.8
Context Window 262K tokens Output limit: 183K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

NVIDIA: Nemotron 3 Ultra is a large language model API from NVIDIA, part of its Nemotron 3 model family. Priced at $0.600 per million input tokens and $2.40 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 4× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. A large 262K-token context window (≈393 pages of text) lets it take in whole books, large codebases, or lengthy transcripts in a single call. On Artificial Analysis's Intelligence Index it scores 23 (D grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $0.600 NT$19.2
Output per 1M tokens $2.40 NT$76.8
Cached Input per 1M tokens $0.120 NT$3.8

Provider
NVIDIA
Model Family
Nemotron 3
Version String
nvidia/nemotron-3-ultra-550b-a55b
Status
Active
Modality
Text
Context Window
262,144 tokens
Output Limit
182,520 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Agentic Index 22 D Measured: 2026-09-08
Coding Index 49 A Measured: 2026-09-08
Intelligence Index 23 D Measured: 2026-09-08

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 79.3% A Measured: 2026-09-08
GPQA Diamond 86.7% S Measured: 2026-09-08
HLE 28.4% A Measured: 2026-09-08
IFBench 81.4% A Measured: 2026-09-08
Non-Hallucination 70.3% Measured: 2026-09-08
Omniscience Accuracy 22.6% Measured: 2026-09-08
SciCode 40.3% B Measured: 2026-09-08
Tau2 83.3% Measured: 2026-09-08
TerminalBench 36.4% Measured: 2026-09-08

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 2.3s Measured: 2026-09-08
Output Speed 168 t/s Measured: 2026-09-08
Response Time 18.9s Measured: 2026-09-08

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.120 OpenRouter
Output $2.40 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter
Input $0.625 OpenRouter
Cached Input $0.188 OpenRouter
Output $3.13 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • NVIDIA: Nemotron 3 Ultra Input price: $0.6/M tokens
  • NVIDIA: Nemotron 3 Ultra Output price: $2.4/M tokens
  • Context window: 262,144 tokens
  • Provider: NVIDIA
  • Model family: Nemotron 3
  • Modalities: Text
  • Data source: OpenRouter, updated daily