# Nemotron 3 Ultra now available on AI Gateway

By Steven Van · 2026-06-04

The open Nvidia model offers a 1M token context window, up to 350 tokens per second, and up to 30% lower cost on agentic tasks.

Nvidia's Nemotron 3 Ultra is now available through [Vercel](<https://creatorstoolbox.com/tools/vercel>)'s AI Gateway. It's an open Mixture-of-Experts reasoning model with a 1M token context window, built for multi-turn agent workflows: planning, tool use, sub-agent delegation, and error recovery.

Nvidia puts throughput at up to 350 tokens per second, with up to 30% lower cost on agentic tasks. To use it, set the model to **nvidia/nemotron-3-ultra-550b-a55b** in the AI SDK. Usage across models can be tracked on the AI Gateway's [model leaderboard](<https://vercel.com/ai-gateway/leaderboards>).

[![](<https://assets.vercel.com/image/upload/contentful/image/e5382hct74si/6mTpZofxZaXoqLWiRMrwVg/444a2908372f9b74327d4df9f02ab7fb/model_leaderboards_og_card.png>)](<https://vercel.com/ai-gateway/leaderboards>)

![Vercel](<https://www.google.com/s2/favicons?domain=vercel.com&sz=128>)

Vercel

The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.

[View Vercel →](<https://creatorstoolbox.com/tools/vercel>)

Sources

[Original source](<https://vercel.com/ai-gateway/leaderboards>)

[Read Nemotron 3 Ultra now available on AI Gateway on Creators Toolbox](<https://creatorstoolbox.com/blog/vercel-nemotron-3-ultra-now-available-on-ai-gateway>)

---
Canonical source: https://creatorstoolbox.com/blog/vercel-nemotron-3-ultra-now-available-on-ai-gateway