LLM Reference
OpenRouter

Nemotron 3 Ultra on OpenRouter

Nemotron 3 · NVIDIA AI

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Nemotron 3 Ultra on OpenRouter?

OpenRouter offers Nemotron 3 Ultra with pay-as-you-go pricing at $0.50/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Input / 1M
$0.50
Output / 1M
$2.20
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: nvidia/nemotron-3-ultra-550b-a55b
Model ID
nvidia/nemotron-3-ultra-550b-a55b

Request example

Curated snippets for this provider are not sourced yet. Use OpenRouter documentation with model ID nvidia/nemotron-3-ultra-550b-a55b.

Gotchas

  • Use provider model ID "nvidia/nemotron-3-ultra-550b-a55b", not the LLMReference slug "nemotron-3-ultra".

Pricing

TypePrice (per 1M)
Input tokens$0.50
Output tokens$2.20

Capabilities

Reasoning

About Nemotron 3 Ultra

NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). Highest Artificial Analysis Intelligence Index for any US open model (score: 48). 300+ tokens/second. 1M-token context. Announced at Computex 2026. Pricing: ~$0.60/$2.60 per 1M tokens (provider median); free tier on some providers.

FAQ

What does Nemotron 3 Ultra cost on OpenRouter?

On OpenRouter, Nemotron 3 Ultra costs $0.5 per 1M input tokens and $2.2 per 1M output tokens.

What is the context window for Nemotron 3 Ultra on OpenRouter?

Nemotron 3 Ultra supports a 1m token context window on OpenRouter.

What API model ID do I use for Nemotron 3 Ultra on OpenRouter?

Use the model ID nvidia/nemotron-3-ultra-550b-a55b when calling OpenRouter's API.

Who created Nemotron 3 Ultra?

Nemotron 3 Ultra was created by NVIDIA AI as part of the Nemotron 3 model family.

Is Nemotron 3 Ultra open source?

Nemotron 3 Ultra has open weights under NVIDIA Open Model according to the seed data, but that does not necessarily mean an OSI-approved open-source license.

Get Started

Model Specs

Released2026-06-04
Parameters550B
Context1m
ArchitectureMixture of Experts