Loading video...

Video Failed to Load

Go Home

DigitalOcean Inference Router is now available through OpenCode & setup is 3 steps. ☁️🆕🤝 Run/connect & it automatically routes to the right model for the job. No more paying frontier prices for a commit message.

digitalocean's profile picture

DigitalOcean

221,376 subscribers

19,798 views • 19 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

#Heroku is transitioning to a “sustaining engineering model”, or dev-speak for no new roadmap. 👀 Let us help you migrate your workloads to an Inference Cloud delivering trusted performance, radically simpler operations, and predictable economics—DigitalOcean. We’re ready to help you evaluate your options in a way that is realistic, structured, and built for the long term. 🌊
0:23

#Heroku is transitioning to a “sustaining engineering model”, or dev-speak for no new roadmap. 👀 Let us help you migrate your workloads to an Inference Cloud delivering trusted performance, radically simpler operations, and predictable economics—DigitalOcean. We’re ready to help you evaluate your options in a way that is realistic, structured, and built for the long term. 🌊

DigitalOcean

10,297 views • 4 months ago

Stop overpaying for every LLM call. 💸 The DigitalOcean Inference Router resolves intent in ~200ms and beats GPT-5.1 and Claude Sonnet 4.5 on routing accuracy. Powered by Rust, WASM, and purpose-built SLMs, it adds milliseconds, not seconds, to every request. 🌊
0:40

Stop overpaying for every LLM call. 💸 The DigitalOcean Inference Router resolves intent in ~200ms and beats GPT-5.1 and Claude Sonnet 4.5 on routing accuracy. Powered by Rust, WASM, and purpose-built SLMs, it adds milliseconds, not seconds, to every request. 🌊

DigitalOcean

19,853 views • 26 days ago

.Character.AI, AMD, & #DigitalOcean are scaling the Qwen3-235B open-weight Mixture-of-Experts AI model to serve approximately 20M users. 🤖📈☁️ This required tuning a 5600/140 (ISL/OSL) workload with FP8 inference on AMD Instinct™ MI325X GPUs to maximize request throughput (QPS).
0:23

.Character.AI, AMD, & #DigitalOcean are scaling the Qwen3-235B open-weight Mixture-of-Experts AI model to serve approximately 20M users. 🤖📈☁️ This required tuning a 5600/140 (ISL/OSL) workload with FP8 inference on AMD Instinct™ MI325X GPUs to maximize request throughput (QPS).

DigitalOcean

27,650 views • 5 months ago

From POC to production inference. 🤖🌁 Join us at #DOdeploy in San Francisco where we'll discuss inference-first architectures, predictable inference economics, operational simplicity at scale, & more.
0:26

From POC to production inference. 🤖🌁 Join us at #DOdeploy in San Francisco where we'll discuss inference-first architectures, predictable inference economics, operational simplicity at scale, & more.

DigitalOcean

12,195 views • 3 months ago

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.
0:49

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.

Factory

2,162,132 views • 14 days ago

#DigitalOcean has everything #AI #Developers need and Deploy is the perfect place to see what we mean. ☁️👩‍💻👨‍💻💯 Register now to attend in-person or virtually. 🔗
0:20

#DigitalOcean has everything #AI #Developers need and Deploy is the perfect place to see what we mean. ☁️👩‍💻👨‍💻💯 Register now to attend in-person or virtually. 🔗

DigitalOcean

558,341 views • 1 year ago

.Ping Proxies is scaling globally with #DigitalOcean. ☁️📈🌍 With the help of DigitalOcean's global infrastructure & Hatch program, Ping Proxies delivers low-latency, scalable proxy services across Europe, the U.S., & Asia, enhancing performance & reliability for their customers. 🔗
0:23

.Ping Proxies is scaling globally with #DigitalOcean. ☁️📈🌍 With the help of DigitalOcean's global infrastructure & Hatch program, Ping Proxies delivers low-latency, scalable proxy services across Europe, the U.S., & Asia, enhancing performance & reliability for their customers. 🔗

DigitalOcean

83,178 views • 1 year ago

Today at NVIDIA GTC, DigitalOcean & NVIDIA delivered the biggest AI infrastructure announcements of the year for teams building in production. 🤖🌩️🚀 More models, next-gen compute, a new US East region, & a workflow that takes you from #NVIDIA prototype to DigitalOcean production without the friction. 🌊
0:26

Today at NVIDIA GTC, DigitalOcean & NVIDIA delivered the biggest AI infrastructure announcements of the year for teams building in production. 🤖🌩️🚀 More models, next-gen compute, a new US East region, & a workflow that takes you from #NVIDIA prototype to DigitalOcean production without the friction. 🌊

DigitalOcean

13,026 views • 3 months ago

1-Click Deploy is here. 🦞☁️💧 Developers can quickly provision always-on agentic AI in a production environment with scalable, reliable infrastructure from #DigitalOcean.
0:24

1-Click Deploy is here. 🦞☁️💧 Developers can quickly provision always-on agentic AI in a production environment with scalable, reliable infrastructure from #DigitalOcean.

DigitalOcean

30,749 views • 4 months ago

#Developers, looking to scale your business? ✨ #DigitalOcean’s got the tools you need—powerful GPUs + expert guides to level up your #AI & #MachineLearning. 🚀☁️ Join us at Deploy in Austin, TX to learn how to run AI/ML workloads & scale effortlessly with DigitalOcean. 🔗
0:20

#Developers, looking to scale your business? ✨ #DigitalOcean’s got the tools you need—powerful GPUs + expert guides to level up your #AI & #MachineLearning. 🚀☁️ Join us at Deploy in Austin, TX to learn how to run AI/ML workloads & scale effortlessly with DigitalOcean. 🔗

DigitalOcean

33,403 views • 1 year ago

Crusoe Managed Inference is now available. Run model inference faster, easier, and more cost-effectively. Large-context AI solutions demand fast outputs, massive throughput, and resilient scaling. Crusoe Managed Inference delivers breakthrough speed & reduced input-token spend.
1:21

Crusoe Managed Inference is now available. Run model inference faster, easier, and more cost-effectively. Large-context AI solutions demand fast outputs, massive throughput, and resilient scaling. Crusoe Managed Inference delivers breakthrough speed & reduced input-token spend.

Crusoe

12,096,815 views • 6 months ago

.AMD Instinct™ MI350X GPU Droplets are live on DigitalOcean's Agentic Inference Cloud. 🆕 Lower latency. Higher throughput. ✅ Transparent pricing and production-ready scale. ✅ AI without the infrastructure headache. 💯
0:22

.AMD Instinct™ MI350X GPU Droplets are live on DigitalOcean's Agentic Inference Cloud. 🆕 Lower latency. Higher throughput. ✅ Transparent pricing and production-ready scale. ✅ AI without the infrastructure headache. 💯

DigitalOcean

25,539 views • 3 months ago

Scale your business, not your costs. ☁️📈 Touch values #DigitalOcean's simplicity, transparent pricing, & responsive support—allowing them to focus on innovation & user experience without getting bogged down by backend management. 🔗
0:23

Scale your business, not your costs. ☁️📈 Touch values #DigitalOcean's simplicity, transparent pricing, & responsive support—allowing them to focus on innovation & user experience without getting bogged down by backend management. 🔗

DigitalOcean

71,807 views • 1 year ago

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️
0:25

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️

DigitalOcean

39,063 views • 1 month ago

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API
0:20

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API

Morph

19,160 views • 13 days ago

Hermes agent doesn't need a frontier model to run your computer well. Kimi K2.6 or Qwen 3.6 can do the same job at a fraction of the cost, and both are available fully private through the Venice API. 🧵 Here's the full Hermes "computer_use" setup:
0:46

Hermes agent doesn't need a frontier model to run your computer well. Kimi K2.6 or Qwen 3.6 can do the same job at a fraction of the cost, and both are available fully private through the Venice API. 🧵 Here's the full Hermes "computer_use" setup:

Venice

24,784 views • 20 days ago

We built a live job board of all the frontier labs hiring right now. Plus a way to see news, funding rounds, compare model releases and more. Monitor the frontier at:
0:38

We built a live job board of all the frontier labs hiring right now. Plus a way to see news, funding rounds, compare model releases and more. Monitor the frontier at:

MTS

895,862 views • 26 days ago

M&S Leicester Make no doubt about it .. this is why everyone is paying through the roof for food. Shoplifting is increasing your food shopping
0:20

M&S Leicester Make no doubt about it .. this is why everyone is paying through the roof for food. Shoplifting is increasing your food shopping

WeGotitBack 🏴󠁧󠁢󠁥󠁮󠁧󠁿🇬🇧🇺🇸

64,604 views • 9 months ago

New paint now available for the new Model Y & 3 in North America
0:36

New paint now available for the new Model Y & 3 in North America

Tesla North America

1,562,503 views • 1 year ago