LLM Pricing

← All Models

NVIDIA: Nemotron 3 Ultra

🇺🇸 NVIDIA · Nemotron 3

Input Price $0.500 per million tokens NT$16.0
Output Price $2.20 per million tokens NT$70.4
Context Window 262K tokens Output limit: 16K
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 $0.500 per million input tokens and $2.20 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 38 (B 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 $0.500 NT$16.0
Output per 1M tokens $2.20 NT$70.4
Cached Input per 1M tokens $0.100 NT$3.2

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
16,384 tokens

Index Metrics

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

Agentic Index 27 C Measured: 2026-08-29
Coding Index 49 A Measured: 2026-08-29
Intelligence Index 38 B Measured: 2026-08-29

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 71.0% B Measured: 2026-08-29
GPQA Diamond 86.7% S Measured: 2026-08-29
HLE 28.4% A Measured: 2026-08-29
HLE 28.4% A Measured: 2026-08-29
IFBench 81.4% A Measured: 2026-08-29
Non-Hallucination 70.3% Measured: 2026-08-29
Omniscience Accuracy 22.6% Measured: 2026-08-29
SciCode 39.9% B Measured: 2026-08-29
Tau2 83.3% Measured: 2026-08-29
TerminalBench 36.4% Measured: 2026-08-29

Performance Metrics

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

First Token Latency 4.0s Measured: 2026-08-29
Output Speed 93 t/s Measured: 2026-08-29
Response Time 33.8s Measured: 2026-08-29

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 $0.100 OpenRouter
Output $2.20 OpenRouter
Input $0.500 OpenRouter
Cached Input $0.100 OpenRouter
Output $2.20 OpenRouter
Input $0.500 OpenRouter
Cached Input $0.100 OpenRouter
Output $2.20 OpenRouter
Input $0.500 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.200 OpenRouter
Output $3.60 OpenRouter

Key Insights

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

  • NVIDIA: Nemotron 3 Ultra Input price: $0.5/M tokens
  • NVIDIA: Nemotron 3 Ultra Output price: $2.2/M tokens
  • Context window: 262,144 tokens
  • Provider: NVIDIA
  • Model family: Nemotron 3
  • Modalities: Text
  • Data source: OpenRouter, updated daily