正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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. ✨

DigitalOcean

226,742 subscribers

595,422 次观看 • 5 个月前 •via X (Twitter)

科学技术财经

Anya Rossi• Live Now

Private livecam show

18 条评论

DigitalOcean 的头像

DigitalOcean5 个月前

Take a closer look at the architecture. 🔗

Ghany Prawira 的头像

Ghany Prawira4 个月前

Hey @digitalocean I really need your help, our app is down now with 1.8m users, support request id: #12506818

DigitalOcean 的头像

DigitalOcean4 个月前

Hi Ghany, we're sorry to hear that, our team is looking into and will respond immediately.

روباهِ آبنبات فروش 的头像

روباهِ آبنبات فروش5 个月前

Your new UI is DOPE digitalocean 🍻

Terminoid 的头像

Terminoid4 个月前

hey, why can't any AMD GPU droplets be created? is there a plan to add more capacity?

DigitalOcean 的头像

DigitalOcean4 个月前

Hi there, thanks for reaching out. Right now AMD GPU Droplets are experiencing capacity constraints, which is why new instances may not be available. Our team is actively working on expanding capacity, but we don't have an ETA to share at the moment. If you'd like us to take a closer look at your specific account, please open a support ticket here: If you already have a ticket open, feel free to DM us the ticket number and we'll be happy to check on it for you.

zahid khan 的头像

zahid khan5 个月前

Very poor customer support. Urgent tickets take 2–3 days to get a response, which is unacceptable for business-critical services. Based on my experience, I would not recommend DigitalOcean to other users until they significantly improve their support quality and response times

Coding_Bishop 的头像

Coding_Bishop3 个月前

@digitalocean I've been trying every possible way to get back into development, but without a laptop I'm stuck. I fell behind after several difficult years. One donated or refurbished laptop could give me the chance to start again. ■

Khaerul Amy 的头像

Khaerul Amy3 个月前

Has DigitalOcean stopped offering the $200 free credit for new customers?

zhao 的头像

zhao4 个月前

dm

Sai Prakash 的头像

Sai Prakash4 个月前

This is useless if you can't be reliable in production scenarios. Whoever at DO decided that on the eve of a major holiday, we should switch people to prepaid balances that DON'T EVEN WORK is a clown. Serverless inference that is unreliable in today's AI-centric world is pointless.

DigitalOcean 的头像

DigitalOcean4 个月前

We apologize for the inconvenience this may caused you. We have requested the Support Department to review your Ticket #12538940 as soon as possible and they will update you shortly. Thank you for your patience with us.

Melissa Kang 的头像

Melissa Kang5 个月前

Outstanding work, let's discuss a potential partnership 🚀

安叫兽|Bird🕊️ 🔶 BNB 的头像

安叫兽|Bird🕊️ 🔶 BNB4 个月前

听着挺省心，关键是路由判断别翻车

Super Chris 的头像

Super Chris3 个月前

You offered my business $200 in free inference credits, and your customer service won't let me use them. They keep telling me I'm not supposed to be able to use it for inference. I would never use your services after this.

DeFiNatti 的头像

DeFiNatti5 个月前

The dedication is clearly visible 🔥

舟底　満哉的头像

舟底　満哉4 个月前

📝

Thomas Samuel 的头像

Thomas Samuel5 个月前

Found your company through the GitHub Education Pack, claimed the yearly student credits, and started building on it only to get an email saying you’re pulling the rug. If I have to pay, I’ll pay another company

相关视频

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.

DigitalOcean

672,368 次观看 • 3 个月前

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.

DigitalOcean

2,192,364 次观看 • 3 个月前

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 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

20,992 次观看 • 5 个月前

DigitalOcean Inference Router is now cache-aware. 🔀 Before, switching models mid-conversation meant losing your cache, and the savings and consistency it bought you. Now, Inference Router weighs that cost before switching. Set a model affinity header or routing budget for full control.

DigitalOcean Inference Router is now cache-aware. 🔀 Before, switching models mid-conversation meant losing your cache, and the savings and consistency it bought you. Now, Inference Router weighs that cost before switching. Set a model affinity header or routing budget for full control.

DigitalOcean

318,497 次观看 • 2 个月前

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. 🌊

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 次观看 • 5 个月前

.DeepSeek-V4-Pro-0813 is live on DigitalOcean Serverless Inference and Inference Router. 🚀 1.6T params / 49B active, 1M-token context, AA Intelligence Index of 53 at max reasoning effort.

.DeepSeek-V4-Pro-0813 is live on DigitalOcean Serverless Inference and Inference Router. 🚀 1.6T params / 49B active, 1M-token context, AA Intelligence Index of 53 at max reasoning effort.

DigitalOcean

347,944 次观看 • 2 个月前

.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).

.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

27,766 次观看 • 10 个月前

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. ⬇️

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 次观看 • 6 个月前

Introducing Runway Media Router. The first preference-optimized router for generative media. Instead of hand-picking a model for every request, you define what "best" means once, for cost, quality, or latency, and the router selects the right video, image, or audio model automatically. Live now in Runway Dev.

Introducing Runway Media Router. The first preference-optimized router for generative media. Instead of hand-picking a model for every request, you define what "best" means once, for cost, quality, or latency, and the router selects the right video, image, or audio model automatically. Live now in Runway Dev.

Runway

62,291 次观看 • 3 个月前

.Grok Build is on DigitalOcean Marketplace. 🆕☁️🤖 SSH in. Run grok. Build. @xAI's coding agent, pre-configured on DigitalOcean Serverless Inference.

.Grok Build is on DigitalOcean Marketplace. 🆕☁️🤖 SSH in. Run grok. Build. @xAI's coding agent, pre-configured on DigitalOcean Serverless Inference.

DigitalOcean

811,156 次观看 • 4 个月前

.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. 💯

.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 次观看 • 8 个月前

Today we're releasing Not Diamond… The world’s most powerful AI model router. Not Diamond maximizes LLM output quality by automatically recommending the best LLM on every request at lower cost and latency. And it takes <5m to set up. Watch this to see how to start using it:

Today we're releasing Not Diamond… The world’s most powerful AI model router. Not Diamond maximizes LLM output quality by automatically recommending the best LLM on every request at lower cost and latency. And it takes <5m to set up. Watch this to see how to start using it:

Tomas Hernando Kofman

77,146 次观看 • 2 年前

.RadixArk brought DeepSeek 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.

.RadixArk brought DeepSeek 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.

DigitalOcean

13,868 次观看 • 4 个月前

Introducing typesafe/jev-router: a cache-aware model router powered by Jev and TypeSafe AI The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻

Introducing typesafe/jev-router: a cache-aware model router powered by Jev and TypeSafe AI The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻

OpenRouter

1,334,841 次观看 • 1 个月前

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.

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 次观看 • 8 个月前

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

Uomi

19,017 次观看 • 4 个月前

#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. 🌊

#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 次观看 • 9 个月前

Glean post-trained NVIDIA Nemotron 3 Nano for enterprise search and got 50% lower latency and 25% fewer tokens, "without any sort of loss in accuracy." That's the example NVIDIA's Shashank Verma gave on the Serve track at Open Intelligence Summit, behind a bigger point: "a model can be open source and frontier at the same time." Serve track, Open Intelligence Summit.

Glean post-trained NVIDIA Nemotron 3 Nano for enterprise search and got 50% lower latency and 25% fewer tokens, "without any sort of loss in accuracy." That's the example NVIDIA's Shashank Verma gave on the Serve track at Open Intelligence Summit, behind a bigger point: "a model can be open source and frontier at the same time." Serve track, Open Intelligence Summit.

DigitalOcean

88,824 次观看 • 28 天前

Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.

Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.

Cursor

2,678,471 次观看 • 3 个月前

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Veeral Patel

1,432,352 次观看 • 2 个月前