Pinned
BLACKBOX AI is now a @Microsoft Official Partner.
Enterprises can purchase @blackboxai licenses directly through the Microsoft Marketplace.
Built for teams that ship fast and stay secure.
BLACKBOX AI
6,107 posts
BLACKBOX AI
@blackboxai
Building Full Self Coding.
- We’re live at London Tech Week 🇬🇧 See agentic inference live at the BLACKBOX AI booth. Don’t miss Richard on Tuesday 9th, 12:30 at the Core Stage: “The Secure Orchestration Layer for the Agentic Enterprise.” Meet us there.
- BLACKBOX AI reposted
Major product updates this week! - BLACKBOX AI reposted"Blackbox AI stands out as the overall leader, ranking first across all three categories: speed, latency, and pricing." YOU ARE WELCOME 🫡
- Nvidia Nemotron 3 Ultra - Output tps Blackbox AI -> 420 CoreWeave -> 261.7 Together AI -> 249.3 Nebius -> 140.7 GMI -> 124.7
00:00 - Well well well... turns out that not all providers are created equal
- We partnered with @nvidia as their single flagship provider and optimized Nemotron 3 Ultra to the highest inference speed served today at 420 output tokens/secNemotron 3 Ultra was launched today, including a focus on low latency agentic performance. We tested it against peers under restricted turn-usage limits on Terminal-Bench v2.1 - @nvidia Nemotron 3 Ultra completes tasks at a much faster pace than peers due to its high inference
- BLACKBOX AI reposted
Nemotron 3 Ultra was launched today, including a focus on low latency agentic performance. We tested it against peers under restricted turn-usage limits on Terminal-Bench v2.1 - @nvidia Nemotron 3 Ultra completes tasks at a much faster pace than peers due to its high inference - BLACKBOX AI repostedthere is a convention in charts to always mention 'higher the better' or 'lower is better' its simpler to keep it 'blackboxer is better'420.2 tok/s on a 550B model. ⚡️ Nemotron-3-Ultra-550B-A55B reaches 420.2 tok/s powered by BLACKBOX AI Inference Engine. Blackbox now delivers the fastest inference in the industry, outperforming every other provider, including on smaller-parameter models. Check our blog in
- Open source needed a comeback. Agents needed real speed. The world needed an American answer. Day 0. @nvidia Nemotron Ultra is live on Blackbox at 420+ tok/s. $0.37 in. $1.08 out. Per million tokens. 550B parameters. Faster than models a fraction of its size. The fastest
- BLACKBOX AI reposted“Why work if you don’t want to be the best?” 🐍420.2 tok/s on a 550B model. ⚡️ Nemotron-3-Ultra-550B-A55B reaches 420.2 tok/s powered by BLACKBOX AI Inference Engine. Blackbox now delivers the fastest inference in the industry, outperforming every other provider, including on smaller-parameter models. Check our blog in
