Nvidia
FrontierAUTO PROFILEPriced via OpenRouter

Nemotron 3 Ultra

text->text

Nemotron 3 Ultra sits in the frontier tier, built for high-capability reasoning, tool use, and long-form output where capability outweighs cost. Available via Nvidia. 262,144-token context. Mid-tier pricing.

Nemotron 3 Ultra is a frontier AI model from Nvidia. It costs $0.5000 per million input tokens and $2.20 per million output tokens (blended $1.01/M), with a 262,144-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.5000/M
per million input tokens
OUTPUT
$2.20/M
per million output tokens
BLENDED 70/30
$1.01/M

-26.6%over 77 days · hover to read

Nemotron 3 Ultra — blended price

Reconstructed from 77 days of recorded rate-card changes. Prices hold flat between changes because that is what a posted price does — no value here is interpolated.

CONTEXT
262,144
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Strong general reasoning
  • Tool use & function calling
  • Long-form writing
  • Production-grade reliability
Typical use cases
  • Production assistants
  • Long-document analysis
  • Multi-step agent workflows
  • Engineering copilots

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Nvidia

See all 6 →

Price history

6 recorded changes
Recorded price changes for Nemotron 3 Ultra, newest first
DateRateWasNowChange
17 Nov 2026Input$0.6000$0.5000-17%
17 Nov 2026Output$2.40$2.20-8.3%
8 Nov 2026Output$3.13$2.40-23%
8 Nov 2026Input$0.6250$0.6000-4%
2 Sept 2026Output$2.50$3.13+25%
2 Sept 2026Input$0.5000$0.6250+25%

Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.

Frequently asked questions

How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra costs $0.5000 per million input tokens and $2.20 per million output tokens, for a blended reference rate of $1.01 per million tokens.

What is Nemotron 3 Ultra's context window?

Nemotron 3 Ultra supports up to 262,144 tokens of context in a single request.

What is Nemotron 3 Ultra best for?

Nemotron 3 Ultra is well suited to Strong general reasoning, Tool use & function calling and Long-form writing.

Who makes Nemotron 3 Ultra?

Nemotron 3 Ultra is developed and served by Nvidia.

Terms used on this page