Find a model

Search models and open their dedicated profile. Use the arrow keys to navigate and Enter to open.

Nemotron 3 Ultra (free)

NVIDIA · 1 configuration

Intelligence—
Input / 1M$0
Output / 1M$0
Context1M

Tariff: OpenRouter · Source: openrouter · USD per million tokens

Thinking configuration

What does more thinking buy you?

Compare this model’s measured thinking configurations.

◌

No pair of measurements available

Change the filters or pick another benchmark. Missing values are not estimated.

Selected: thinking default · Click a point to switch configuration

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...

This model is in the catalog but has no imported benchmarks. Capabilities are not estimated.

Specifications from the catalog

Inputtext
Outputtext
Tool callingYes
Structured outputNo
SpeedNot available
First tokenNot available
Maximum output65.5K
Catalog listing date2026-06-04