DigitalOcean (@digitalocean) / X

DigitalOcean

81.9K posts

DigitalOcean

@digitalocean

The AI-Native Cloud. ☁️ Status: @DOstatus Support: do.co/contact

Joined January 2012

Affiliates Replies Articles Media

Pinned
DigitalOcean
@digitalocean
Jun 6
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. ✨
00:00
DigitalOcean
@digitalocean
9h
Getting @Kimi_Moonshot K3, all 2.8T parameters of it, production-ready and fast on day zero is complex. We take on that complexity so you don't have to. Serving recipe tuned with the @vllm_project team for @nvidia HGX™ B300 and @AMD Instinct™ MI350X GPUs, verified against
DigitalOcean
@digitalocean
14h
A missed phone call can mean a senior goes without the care they need. ConfirmOk built its whole business on making sure that never happens. Outages on their old platform put daily wellness checks at risk. Now they run on App Platform & Managed PostgreSQL, reliable enough that
00:00
DigitalOcean
@digitalocean
18h
Don't just pick a model. Route to the right one for each task. 💯 At the @BerkeleyRDI Agentic AI Summit this weekend, we'll show how teams orchestrate models around cost, latency, task type, and user preference. See you at @UCBerkeley! 🗓️📌 do.co/4cavn5I
DigitalOcean
@digitalocean
Jul 29
Stop paying to reprocess the same context on every LLM request. 🛑 Prompt Caching on DigitalOcean AI-Native Cloud automatically caches shared context like system prompts, tool definitions, and reference docs, reducing the cost of repeated input tokens by up to 80% with no code
00:00
See @digitalocean's full profile
Sign up
Log in

See @digitalocean's full profile

See @digitalocean's full profile