AtlasAI Center AI tool intelligence
Search
NVIDIA · API model

Nemotron 3 Ultra (free)

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
1M
Input / 1M
Free
Output / 1M
Free
Released
Jun 4, 2026
View on OpenRouterFind it in the catalog
Specifications

Nemotron 3 Ultra (free) specs

Provider
NVIDIA
Type
API model
Model ID
nvidia/nemotron-3-ultra-550b-a55b:free
Context window
1,000,000 tokens1M
Input price
Freeper 1M input tokens
Output price
Freeper 1M output tokens
Accepts
text
Produces
text
Released
Jun 4, 2026
Popularity
41/100position #14 in OpenRouter's weekly usage ranking
Source
OpenRouter
Overview

About Nemotron 3 Ultra (free)

Nemotron 3 Ultra (free) is an API model from NVIDIA, released on Jun 4, 2026, with a context window of 1,000,000 tokens, pricing of Free per million input tokens and Free 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 Free.

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 callingReasoning
FAQ

Nemotron 3 Ultra (free) questions

What is the context window of Nemotron 3 Ultra (free)?

Nemotron 3 Ultra (free) supports a context window of 1,000,000 tokens.

How much does Nemotron 3 Ultra (free) cost?

Nemotron 3 Ultra (free) is listed at Free per million input tokens and Free per million output tokens on OpenRouter.

When was Nemotron 3 Ultra (free) released?

Nemotron 3 Ultra (free) was published on Jun 4, 2026.

What inputs does Nemotron 3 Ultra (free) accept?

Nemotron 3 Ultra (free) accepts text input and produces text output.