Nemotron 3 Ultra: API pricing, context window and capabilities

Prices from official vendor price lists · October 2026

Nemotron 3 Ultra costs $0.625 per 1M input tokens and $3.13 per 1M output tokens, with a 262.1K context window. Mid-priced: dearer than 63% of this rating, with Nemotron 3 Super as the nearest cheaper NVIDIA option. Recorded for reasoning, open weights.

Visit NVIDIA All NVIDIA models

Capabilities

API $/1M (in / out)

$0.625 / $3.125

Context window

262.1K tokens

Price / mo

API only

Overview Reviews

Nemotron 3 Ultra is an AI model from NVIDIA, priced at $0.625 input and $3.125 output per 1M tokens. That places it in the mid tier of this rating — dearer than 63% of the 205 priced models listed.

It holds 262.1K tokens in a single conversation. Capabilities recorded in this rating: text & chat, reasoning, tool calling, frontier tier, multilingual. Access is through the API rather than a consumer subscription.

API price$0.625 / $3.125per 1M tokens, in / out

Context262.1K tokenstokens per conversation

VendorNVIDIAall models from this vendor

TierMiddearer than 63% of models

Cost calculator

1M tokens/mo10M tokens/mo50M tokens/mo200M tokens/mo

Standard$2.50~~AED 9 per month~~

With batch −50%$1.25~~AED 5 per month~~

With caching on input$2.36~~AED 9 per month~~

Standard$25.00~~AED 92 per month~~

With batch −50%$12.50~~AED 46 per month~~

With caching on input$23.59~~AED 87 per month~~

Standard$125~~AED 459 per month~~

With batch −50%$62.50~~AED 230 per month~~

With caching on input$118~~AED 433 per month~~

Standard$500~~AED 1,836 per month~~

With batch −50%$250~~AED 918 per month~~

With caching on input$472~~AED 1,733 per month~~

Assumes a 1:3 input-to-output ratio, which is typical for chat and generation. Dirham figures use 3.6725 per dollar. Batch and caching discounts apply where the vendor offers them.

Compared with alternatives

How Nemotron 3 Ultra sits against its neighbours in this rating. Tap a card to open that model.

GLM 5.2

Cheaper

Z.ai

$0.966 / $3.0361.05M tokens

DeepSeek V4 Pro 0813

Closest match

DeepSeek

$1.0494 / $3.14821.05M tokens

DeepSeek V4 Pro 0813

Step up

DeepSeek

$1.0494 / $3.14821.05M tokens

Good and poor fit

Good fit

Multi-step analysis, planning and code review, where the first plausible answer is often wrong.
General text generation and conversation across languages.

Poor fit

Classification, routing and short summaries — a small model does these identically for a fraction of the price.
Anything requiring image input — this model does not accept it.

Related filters

Text & chat234 models for text generation and chat

Reasoning175 models that think before answering

Tool calling172 models that call your functions

Frontier tier42 flagship models, the best each vendor sells

MultilingualAll 245 models work beyond English

NVIDIA6 models from this vendor

All 245 modelsThe full rating with filters and prices

Frequently asked questions

How much does Nemotron 3 Ultra cost?

$0.625 / $3.125 per 1M tokens, input and output. In dirhams that is roughly AED 2.30 per 1M input tokens. Batch processing halves it where the vendor offers it.

What is the context window of Nemotron 3 Ultra?

262.1K tokens in a single conversation.

What can Nemotron 3 Ultra do?

In this rating it is recorded with: text & chat, reasoning, tool calling, frontier tier, multilingual, open weights.

Is Nemotron 3 Ultra a good choice?

It depends on the job. See the good-fit and poor-fit lists above, and compare against the neighbouring models before committing.

Ratings 0

Avg. score 0

Rate this page

Help us improve