DigitalOcean

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. ✨

@amit_sachan Thank you for flagging this, we understand the urgency given the impact on production. We can see you've already opened ticket 12587216, and we're escalating this internally to our team for immediate review.

@digitalocean Urgent help needed from DigitalOcean Support. Our production DOKS cluster in BLR1 has intermittent outbound TCP/443 failures across multiple worker nodes. This is affecting image pulls and production API calls. Ticket: [12587216]. Please escalate.

The AI debate today is framed as open vs. closed weights. I think that's already becoming the wrong question especially with the new @Kimi_Moonshot K3 release. Weights are just a snapshot. They age. They commoditize. The real strategic asset is the intelligence you build on top of them - your data, RL loops, evaluations, workflows, agents, and proprietary context. In other words: Own your data. Own your workflows. Own your intelligence. That's where durable advantage will come from. My latest thoughts ↓ x.com/paddix/status/…

@nenharma82 Thank you for sharing the ticket number. We have requested the Support Department to expedite this ticket and they will update you shortly. Thank you for your patience in this matter.

@digitalocean Thank you very much for the quick reply! The ticket is open again #12581042

@digitalocean why did you auto-close my ticket about a prod db cluster that suddenly went offline? I can't even restore from backup... I really need that data back! I need some help here, please.

@ezsmith397 Hi Smith, that’s not the experience we want for you. Please DM your email ID so we can check what’s going on

@digitalocean And after 3 nightmare tries to get through this it errored out still. On to the next provider.

Absolute worst captcha type experience I've ever seen, what the heck @digitalocean

@piyush0101 50% lower costs. 2x throughput. Zero re-platforming. Catch the session on July 22nd @ 4pm to learn we did it. 👀

Excited to speak at AMD Advancing AI this year. I'll be talking about the biggest challenge AI developers face. Not just getting GPUs, but using them to their full potential. Whether it’s tokenmaxxing or performance optimization, DigitalOcean has deeply invested in helping builders achieve their goals. If you're going to be there, come to the session July 22nd, 4pm, Room 2010 or find me at booth #435! Every AI company hits a cost cliff. At AMD Advancing AI 2026, I'm showing how DigitalOcean cut Character.AI's inference costs by 50% and doubled throughput — no re-platforming. 🎥 Live demo: prefix-aware routing reclaiming ~350ms of compute per cache hit — hundreds of GPU-hours/day at scale. You'll leave knowing: → Why lower cost and faster inference are the same optimization, not a trade-off → How our open-source Inference Gateway + vLLM/AMD work makes this real → How Plano routes each request to the right model in <200ms, zero code changes If inference economics keep you up at night, this talk's for you. Catch me after at booth #435. 👋 #AdvancingAI2026 #AMD #DigitalOcean #Inference

@Nateroberteze Hey Nate, thank you for reaching out! Sorry to hear about this. We will send you a DM right away to collect your information and have this looked into in more detail.

@digitalocean URGENT 🚨 our production account was just terminated and our managed MySQL database deleted over a single failed payment. The only notice was a low-severity "please top up" email 3 days ago nothing warning that the account or data would be destroyed.

@VictorSuOrtiz @AMD @weaviate_io @radixark @lmsysorg We can't wait to hear your expert perspective on native multimodality, @VictorSuOrtiz. Going to be a great discussion for all of those attending! 💯

Excited to join @digitalocean, @AMD, @weaviate_io, @RadixArk, and @lmsysorg for the Advancing AI kickoff on July 21 🤝 I’ll be sharing a few perspectives on native multimodality, then sticking around for good conversations 🍻 See you there!

@MiniMax_AI @AMD @weaviate_io @radixark We're so excited to to co-host this with you, @MiniMax_AI! 🙌

We’re joining @digitalocean, @AMD, @weaviate_io, @RadixArk, and LMSYS for the Advancing AI kickoff on July 21 🤝 Expect lightning talks ⚡ live demos 🛠️ and a MiniMax session on native multimodality—followed by drinks, bites, and conversations with the builders advancing AI 🍻 See you there!

We're excited to share that @MiniMax_AI & @weaviate_io are joining as co-hosts alongside @radixark. RSVP. 👉 do.co/4vdCMZv

We’re hosting a kickoff for the Advancing AI conference with @AMD, @RadixArk, and friends. Join us for lightning talks, live demos, drinks with the founders, operators, and investors who are advancing AI together. RSVP here. 🎟️ do.co/4vdCMZv

Hello, thank you for contacting us. In order to resolve this issue, we’ll need to create a support ticket for our engineers to review it thoroughly. If you’ve already created a ticket, please share the ticket number with us. Alternatively, we can create the ticket for you—just send us your registered email address in a direct message. You can also create the ticket yourself using our Contact form.

@digitalocean DigitalOcean space is disabled in BLR datacenter. Any idea when that will be up?

Glad to hear SMTP is working now! Thank you also for flagging the issue with the 'new ticket' button. Since you already have an open ticket with us, could you please reply directly to that existing thread with the browser and device details? Our team will gladly investigate this further.

@digitalocean thank you smtp works now i would however suggest you look in to why new ticket button doesnt work from multiple browsers and devices

@digitalocean hello there I have an issue imgur.com/a/4KtBX9Z Well honestly no my issue is that you guys disabled SMTP your server keeps giving my customers 502 and latest two pages don't have SSL certificate but i can't even report it as you have disabled reporting

@radixark Can't wait! 🍻

We'll be there on July 21! Come talk inference, open source, and the latest update for SGLang. See you at the kickoff 🍻 Register: luma.com/zz40nkob?utm_s…

@harryheisme @radixark @deepseek_ai @AMD 🤝

@digitalocean @radixark @deepseek_ai @AMD Thx for collab!

.@radixark brought @deepseek_ai V4 to production with DigitalOcean and @AMD. AMD Instinct™ MI350X GPU Droplets, plus joint engineering that drove a ~10x throughput gain. When the team that builds the inference engine picks your stack, that's the signal.

@richardczl @radixark @deepseek_ai @AMD Back at ya, @richardczl! 🙌

@digitalocean @radixark @deepseek_ai @AMD Thanks for collaboration!!

@ilerien We would request you to kindly review your Email inbox, as the Support team already responded to your query few hours ago. Let us know If you did not receive an email, we will request the department for another follow up. Thank you!

@digitalocean can you provide link

@ilerien We got you. We have created the support ticket: 12565323 on your behalf. Ou team will reach out to you shortly via the ticket. Thank you!

@digitalocean hi @digitalocean if you had checked the gif you would see that i am unable to create ticket but sure if you can resolve at least smtp albatross@raznahotel.lv

@chriskim_dev @ChatGPTapp @Box 👀

New agentic workflow video dropping soon @ChatGPTapp @digitalocean @Box

See the full breakdown. 🔗 do.co/4wCPfX6