Nemotron Ultra by Baseten | AI model information

Use Kimi K3 in OpenCode Go. Get $5 off your first month.

$5 OFF

Discuss

Model details

Nemotron Ultra

Basetennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bnemotron

Open provider page Provider docs

Quick Info

Provider: Baseten
Model key: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Release date: Jun 4, 2026

Cost

Input token cost: $0.60
Output token cost: $2.40

Limits

Output tokens: 202,800 tokens
Context window

Latest news about Nemotron Ultra

Videos about Nemotron Ultra

Recent tweets and retweets from Baseten

Jul 23, 2026, 9:00 PMUTC

We just launched a new tier of Fast Model APIs, starting with GLM-5.2 Fast. Our customers run some of the most demanding, real-time workloads. Model APIs are the fastest way to get running with frontier-level models, and our Fast tier has even tighter guardrails around…

Jul 23, 2026, 8:40 PMUTC

Introducing our new Fast tier of Model APIs, starting with GLM-5.2.

Jul 23, 2026, 8:34 PMUTC

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI. Video

Jul 23, 2026, 8:34 PMUTC

Try it now: app.baseten.co/model-apis/gl…

Jul 23, 2026, 6:08 PMUTC

Everyone assumes owning your inference stack is a later-stage problem. these four founders didn't wait. @QuantumArjun, @thejackobrien, @sadjamz_ , @aquariusacquah, all made that call early. building on it right now with @baseten. Aug 4th, SF. off the record conversation on…