Command Palette
Search for a command to run...

Together AI Says NVIDIA Nemotron 3 Ultra Climbs to 35 Billion Tokens a Day

aiai-modelingai-open-modelsai-infrastructureai-inference-platforms 4 posts · 3 accounts

Together AI reported that NVIDIA Corp’s Nemotron 3 Ultra AI model quickly climbed to 35 billion tokens processed per day on the OpenRouter API marketplace. The platform shared the milestone on X on Wednesday, noting it took just a few days for the open weights model to reach the usage level.

NVIDIA AI’s official account retweeted the data and added a comment celebrating the adoption. OpenRouter serves developers who route large language model inference traffic to various providers, while Together AI hosts the NVIDIA model on its own GPU cloud infrastructure. The surge in daily token volume signals strong developer interest in open models that do not require closed API licensing, positioning the Nvidia offering as a competitive alternative to proprietary models in the AI infrastructure market.

From the sources (4 posts)

@ctnzr

RT @togethercompute: Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's…

@nvidiaai

RT @togethercompute: Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's…

@nvidiaai

@togethercompute @OpenRouter @nvidia LET'S GO

@togethercompute

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting with their tokens for open models that are fast, efficient, and fully customizable. A top open model

Preview built on a synthetic news corpus (16 weeks, Apr–Jul 2026). Impact calls are model reads, not price data.

About Archive