AtlasAI Center AI tool intelligence
Search
NVIDIA · API model

Nemotron 3 Super (free)

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Context
262K
Input / 1M
Free
Output / 1M
Free
Released
Mar 11, 2026
View on OpenRouterFind it in the catalog
Specifications

Nemotron 3 Super (free) specs

Provider
NVIDIA
Type
API model
Model ID
nvidia/nemotron-3-super-120b-a12b:free
Context window
262,144 tokens262K
Input price
Freeper 1M input tokens
Output price
Freeper 1M output tokens
Accepts
text
Produces
text
Released
Mar 11, 2026
Source
OpenRouter
Overview

About Nemotron 3 Super (free)

Nemotron 3 Super (free) is an API model from NVIDIA, released on Mar 11, 2026, with a context window of 262,144 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 Oct 27, 2026. Always confirm current pricing and limits with the provider before production use.

Tool callingStructured outputsJSON modeReasoning
FAQ

Nemotron 3 Super (free) questions

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

Nemotron 3 Super (free) supports a context window of 262,144 tokens.

How much does Nemotron 3 Super (free) cost?

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

When was Nemotron 3 Super (free) released?

Nemotron 3 Super (free) was published on Mar 11, 2026.

What inputs does Nemotron 3 Super (free) accept?

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