Joined January 2012
5,824 Photos and videos
Pinned Tweet
Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨
4
7
27
7,770
.@ScoutAPM is now in the DigitalOcean Marketplace. 🤝🆕 Real-time errors & logs, traced down to code-level, billed straight to your DigitalOcean account. One Bill. Full-stack visibility. ☁️
2
2
9
3,990
You can't trust a model decision you didn't measure on your own workload. DigitalOcean Model Evaluations lets you compare any candidate–frontier, open-weight, or your own router policy–on your own data before you ship. We tested Fable 5, Opus 4.8, and Inference Router; see how they performed.
2
3
18
8,266
.@angelahoover_ is building @andi_search, an AI search engine that actually answers questions, with a 15B-page index that filters out spam. 🔍 They saved on cost & time-to-live while growing to 150k MAUs & launching a new API. Great to have Andi in our Startups Program & watch them grow. 🚀
2
4
13
1,610
DigitalOcean retweeted
Use #Claude Fable 5 from right inside your @digitalocean control plane. Day 0 support for the most advanced models so you can focus on building and not figuring out infrastructure!!
Claude Fable 5 is now on DigitalOcean Serverless Inference. 🚀🆕 @AnthropicAI 's most advanced model for autonomous coding & knowledge work now running right inside your existing DigitalOcean environment. No new stack. No surprise bills. Just reliable inference at scale.
1
3
12
2,708
We're thrilled to welcome three exceptional leaders to DigitalOcean: Kevin Van Gundy (CRO), Leo Leung (CMO), and Brady Mickelsen (CLAO) as we scale the first full-stack AI cloud purpose-built for the inference era—an era that needs its own cloud. We built it, and now we have the team to scale it.
3
3
14
2,920
DigitalOcean retweeted
The difference here is the in the details - treating routing as a performance optimization problem misses the mark for a lot of scenarios. Performance is subjective. Routing is both a decision tree and a preference problem. @digitalocean inference router resolves this tension by catering to both these dimensions while helping you lower your cost and enabling a more powerful model ensemble for your agentic apps
Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨
1
3
8
3,601
Claude Fable 5 is now on DigitalOcean Serverless Inference. 🚀🆕 @AnthropicAI 's most advanced model for autonomous coding & knowledge work now running right inside your existing DigitalOcean environment. No new stack. No surprise bills. Just reliable inference at scale.
3
3
19
5,465
DigitalOcean is heading to London Tech Week. 🇬🇧 📍 Booth 183 — live demos & 1:1 meetings 🍻 June 9 — The Signal: @Techstars Ecosystem Part 🧠 June 10 — Deploy AI in 5 Minutes: A Hands-On Inference Challenge (session) 🕵️ June 11 — The AI Summit
1
1
5
3,165
Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨
4
7
27
7,770
15 product launches. One keynote. A whole team that made it happen. 🤝 Go behind the scenes of Deploy 2026 with the engineers, account executives, & marketers who shipped our AI-Native Cloud. ☁️👀
1
2
9
2,341