AI BriefingNvidia Nemotron 3 Ultra, Now Available on Vercel AI Gateway
Key point
Nvidia's MoE reasoning model **Nemotron 3 Ultra** has launched on Vercel AI Gateway, supporting agentic workflow optimization.
Details
Nvidia's Nemotron 3 Ultra is now available on Vercel AI Gateway. This model is an open Mixture-of-Experts (MoE) reasoning model designed for complex agentic workflows such as planning, tool use, sub-agent delegation, and error recovery.
Key performance and features are as follows:
- Supports a 1M token context window
- Achieves throughput of up to 350 tokens per second
- Reduces costs by up to 30% on agentic tasks
AI Gateway provides a unified API for model calls, ensuring high uptime through usage and cost tracking, retries, failover, and performance optimization. It also passes through provider pricing without additional platform fees, and the same applies to Bring Your Own Key (BYOK) requests.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.