AtlasAI Center AI tool intelligence
NVIDIA · API model

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Context
262K
Input / 1M
$0.6
Output / 1M
$2.4
Released
Jun 4, 2026
Specifications

Nemotron 3 Ultra specs

Provider
NVIDIA
Type
API model
Model ID
nvidia/nemotron-3-ultra-550b-a55b
Context window
262,144 tokens262K
Input price
$0.6per 1M input tokens
Output price
$2.4per 1M output tokens
Accepts
text
Produces
text
Released
Jun 4, 2026
Source
OpenRouter
Overview

About Nemotron 3 Ultra

Nemotron 3 Ultra is an API model from NVIDIA, released on Jun 4, 2026, with a context window of 262,144 tokens, pricing of $0.6 per million input tokens and $2.4 per million output tokens. It accepts text input and produces text output.

At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0084.

Specs are sourced from OpenRouter and were last checked on Nov 3, 2026. Always confirm current pricing and limits with the provider before production use.

Tool callingStructured outputsJSON modeReasoning
FAQ

Nemotron 3 Ultra questions

What is the context window of Nemotron 3 Ultra?

Nemotron 3 Ultra supports a context window of 262,144 tokens.

How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra is listed at $0.6 per million input tokens and $2.4 per million output tokens on OpenRouter.

When was Nemotron 3 Ultra released?

Nemotron 3 Ultra was published on Jun 4, 2026.

What inputs does Nemotron 3 Ultra accept?

Nemotron 3 Ultra accepts text input and produces text output.