Home / Models / NVIDIA / Nemotron 3 Ultra

Nemotron 3 Ultra pricing and routing profile

Nemotron 3 Ultra from NVIDIA lists at $0.60 per million input tokens and $2.40 per million output tokens, with a 262,144-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.60
Output, per 1M tokens$2.40
Cached input, per 1M$0.12
Context window262K
Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.384
Chat reply (2,000 in, 400 out)$2.16
Retrieval-augmented answer (8,000 in, 500 out)$6.00

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Nemotron 3 Ultra. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves Nemotron 3 Ultra

HostInput / output per 1MLog probabilitiesUptime, last 30 min
DeepInfra$0.50 / $2.20no99.9%
BaseTen$0.60 / $2.40no100.0%
BaseTen$0.60 / $2.40no100.0%
Venice$0.625 / $3.13no99.8%

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Nemotron 3 Ultra that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
R1 0528$0.50 / $2.1514%
Kimi K2.5$0.45 / $2.2517%
Qwen3.6 Plus$0.325 / $1.9534%
DeepSeek V4 Flash Vision Exp$0.44 / $1.3235%
Qwen3 235B A22B Thinking 2507$0.23 / $2.3036%
Qwen3 VL 30B A3B Thinking$0.20 / $2.4037%

Compare Nemotron 3 Ultra

Questions

How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra lists at $0.60 per million input tokens and $2.40 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $2.16 per 1,000 requests.

What is the context window of Nemotron 3 Ultra?

262,144 tokens.

Can a cheaper model replace Nemotron 3 Ultra?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Nemotron 3 Ultra on one half of your requests and make at most three answers worse on the other.