DEV Community

DigitalOcean

The AI-Native Cloud for scaling production workloads.

Organization Settings Admin

DigitalOcean is the tech stack of choice for developers worldwide to build agentic AI in the modern era.

www.digitalocean.com Twitter GitHub YouTube LinkedIn Location Broomfield, CO Joined Joined on 
How do I cap inference billing to avoid surprise costs from idle GPUs or runaway agents?
digitalocean_staff profile

How do I cap inference billing to avoid surprise costs from idle GPUs or runaway agents?

#ai #developers #cloud #startup
Comments
3 min read
We moved a production backend from a phone
digitalocean_staff profile

We moved a production backend from a phone

#ai #agents #cloud #database
23
Comments
3 min read
Jev: an AI model that can’t write a sentence
digitalocean_staff profile

Jev: an AI model that can’t write a sentence

#ai #startup #infrastructure #developers
4
Comments 1
8 min read
What is disaggregated prefill and decode in LLM inference?
digitalocean_staff profile

What is disaggregated prefill and decode in LLM inference?

#ai #developers #startup #infrastructure
1
Comments 1
3 min read
How to route LLM requests by cost vs. latency
digitalocean_staff profile

How to route LLM requests by cost vs. latency

#ai #startup #developers #infrastructure
2
Comments 2
4 min read
Which inference provider has both serverless and dedicated GPU tiers on the same platform with one API?
digitalocean_staff profile

Which inference provider has both serverless and dedicated GPU tiers on the same platform with one API?

#ai #infrastructure #llm #startup
Comments 1
3 min read
What It Actually Costs to Serve a 1M-Token Model in Production
digitalocean_staff profile

What It Actually Costs to Serve a 1M-Token Model in Production

#ai #infrastructure #llm #developers
3
Comments
12 min read
AI token billing continues to cause sticker shock
digitalocean_staff profile

AI token billing continues to cause sticker shock

#ai #llm #startup
Comments
5 min read
loading...