# droplets Published articles for droplets. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Introducing v5 Droplets: next-generation performance, sized to your workload DevFeed: [Introducing v5 Droplets: next-generation performance, sized to your workload]() Original publisher: [Read original article]() Author: Krishna Nallamothu Published: 2026-08-26T02:19:47Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [Hardware](), [cpu](), [AI Platform](), [web applications]() Tags: [agentic-ai](), [amd](), [audio](), [compute](), [digitalocean](), [droplets](), [performance](), [product-updates](), [v5](), [video](), [web-applications]() ### AI overview DigitalOcean announces the general availability of v5 Droplets, built on 5th Gen AMD EPYC processors. The release targets demanding workloads and offers independently configurable vCPU, memory, and storage, with up to 30% higher performance per core than previous-generation Droplets. ### Source excerpt We're excited to introduce v5 Droplets, a new generation of compute built on 5th Gen AMD EPYC™ processors. v5 Droplets are purpose built to deliver higher performance for demanding workloads such as compute-intensive agentic AI platforms, AI/ML tools, high throughput audio/video transcoding, and high-traffic distributed web applications and APIs. v5 Droplets deliver up to 30% higher performance per core than our previous-generation Droplets. For the first time, you can select vCPU, memory, and storage independently and pay for only the resources you choose. Your Droplet fits your application, and your bill reflects exactly what you used, nothing more. You can continue creating bundled Droplets the way you're used to, or choose v5 Droplets for next-generation workload-optimized performance. Designed for workloads that need more More teams are building AI applications, agent platforms, bursty data pipelines, and hosting high-traffic web applications on DigitalOcean than ever before, and those workloads demand higher performance. They need the faster cores, flexible memory ratios, and compute configurations that v5 Droplets provide. Starting with v5, every Droplet is tied to a hardware generation, so you get the same silicon and the same performance every time. You can choose Shared Droplets (s5) for bursty, variable work that doesn't need a full dedicated core, or General purpose Droplets (g5) for guaranteed, dedicated CPU, with memory ratios from 2x to 8x per vCPU. Pricing is simple and based on an hourly rate. You see each resource's price as you configure, a running total as you go, and one line per Droplet on your bill. Early customers running game servers and high throughput e-commerce applications saw 2x performance compared to their existing Droplets. No changes to existing Droplets pricing or experience Every existing Droplet plan stays exactly as it is and maintains the same prices, same bundles, same monthly caps, no migrations, and nothing new on your invoi ## Upcoming GPU Pricing Updates DevFeed: [Upcoming GPU Pricing Updates]() Original publisher: [Read original article]() Author: Krishna Nallamothu Published: 2026-07-21T00:30:53Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [GPU](), [model-deployment]() Tags: [2026](), [amd](), [billing](), [capacity](), [compute](), [cost](), [digitalocean](), [droplets](), [gpu](), [inference](), [infrastructure](), [nvidia](), [pricing](), [product-updates](), [training](), [updates]() ### AI overview DigitalOcean announces price increases for select NVIDIA and AMD GPU droplets effective August 1, 2026. Active workloads will be billed at the new rates, while existing reserved contracts retain their locked-in rates until renewal. ### Source excerpt Effective August 1st, 2026, we will be updating prices on select GPUs. This change reflects strong demand for advanced GPU capacity and helps us expand reliable access to high-performance compute for customers. Even with the updated rates, DigitalOcean continues to offer some of the most competitive GPU infrastructure pricing in the market. Below is a detailed breakdown of these upcoming changes and how they affect you. On-Demand GPU Price Adjustments Effective August 1, 2026, on-demand pricing for NVIDIA and AMD GPU droplets will be updated as follows: What this means for your bill: Any active workloads running on or after August 1, 2026 will be billed at the new rate. By continuing to access or use the services on or after August 1, 2026, you are agreeing to accept and pay the updated rates. These changes will be reflected in your total bill on September 1, 2026. If you do not wish to continue using the service at the updated rate, you will need to take action by August 1, 2026 to destroy your GPU Droplets. 12-Month Reserved GPU Price Adjustments For teams running predictable, continuous training or inference workloads, reserved plans remain the most cost-effective way to lock in lower rates. Effective August 1, 2026, we're also adjusting our 12-month reserved pricing: What this means for your bill: If you're currently in a contract with us that locks in your rate, there is no change to your rate. If you choose to renew after your terms expires, your rates will be adjusted to the new 12-month reserved rate outlined above. If you have questions about how these changes will impact your specific workloads, or if you want to explore reserving capacity, please contact our sales team--we're here to help you find the most cost-efficient path forward. Helpful Resources Visit DigitalOcean pricing for the most up-to-date pricing for GPU Droplets and all DigitalOcean products and services. Visit the billing dashboard for the latest on your account bill. Your use of the Digita ## DigitalOcean's Inference Optimized Image improves Llama 3.3 70B inference efficiency on GPU Droplets DevFeed: [DigitalOcean's Inference Optimized Image improves Llama 3.3 70B inference efficiency on GPU Droplets]() Original publisher: [Read original article]() Author: Hemasumanth Rasineni Published: 2026-02-19T14:42:18Z Content type: article Language: en Sources: [DigitalOcean]() Topics: [Inference](), [Digital Ocean](), [Optimization](), [GPU](), [benchmarking](), [Large Language Model](), [llama](), [model-deployment](), [quantization]() Tags: [ai](), [benchmark](), [benchmarking](), [cost](), [digitalocean](), [droplets](), [engineering](), [gpu](), [hardware](), [inference](), [llama](), [optimization](), [quantization](), [running](), [tokens]() ### AI overview This article describes DigitalOcean's Inference Optimized Image, a pre-configured OS image for GPU Droplets that combines several inference optimizations. In the reported test, Llama 3.3 70B achieved higher throughput, lower time to first token, and lower cost per million tokens while running on two H100 GPUs instead of four. ### Source excerpt Production-grade LLM inference demands more than just access to GPUs; it requires deep optimization across the entire serving stack, from quantization and attention kernels to memory management and parallelism strategies. Most teams deploying models like Llama 3.3 70B on vanilla configurations are leaving the majority of their hardware's capability on the table: underutilized FLOPs, wasted memory bandwidth, and GPU hours spent waiting instead of computing. To solve this, we built the Inference Optimized Image a fully pre-configured OS image available on DigitalOcean's GPU Droplets -- that layers speculative decoding, FP8 quantization, FlashAttention-3, paged attention, concurrent optimization, and prompt caching into a single deployable image. The result of our particular test: 143% higher throughput (2,000 vs. 823 tokens/second), 40.7% lower TTFT (187.9ms vs. 316.83ms), and a 75% reduction in cost per million tokens ($1.472 vs. $5.80) -- all while running Llama 3.3 70B on 2 H100 GPUs instead of 4. In this post, we walk through the optimization stack, the engineering reasoning behind each layer, and the benchmark methodology and our test results showing these gains. Prefill, Decode, and Why Optimization is Multiplicative As we covered in our LLM Inference Benchmarking post, inference works in two distinct phases with fundamentally different computation characteristics. The prefill phase processes the entire input prompt through the model's forward pass self-attention, layer norms, feed-forward networks and is compute-bound, with high arithmetic intensity (FLOPs per byte transferred). The decode phase generates tokens one at a time, loading the full weight matrix and KV cache from HBM for each token, making it strictly memory-bandwidth-bound. This distinction matters because each optimization in our stack targets a specific bottleneck. Speculative decoding attacks the sequential nature of decode. FP8 quantization reduces memory footprint and accelerates compute via hig ## Technical Deep Dive: How we Created a Security-hardened 1-Click Deploy OpenClaw DevFeed: [Technical Deep Dive: How we Created a Security-hardened 1-Click Deploy OpenClaw]() Original publisher: [Read original article]() Author: Freddie Rice Published: 2026-01-30T18:36:29Z Content type: article Language: en Sources: [DigitalOcean]() Topics: [OpenClaw](), [Security](), [Digital Ocean](), [Deployment](), [Artificial Intelligence](), [cloud-infrastructure]() Tags: [agentic](), [deployment](), [digitalocean](), [droplets](), [engineering](), [memory](), [openclaw](), [security](), [storage](), [technology]() ### AI overview This technical article describes DigitalOcean's security-hardened 1-Click Deploy OpenClaw offering. It explains the motivation for providing a safer, easier deployment option and identifies priorities including safe communication, isolating agentic code, and preventing attacks from the wider internet. ### Source excerpt OpenClaw, an open source AI assistant (recently renamed from Moltbot, and earlier Clawdbot), has exploded in popularity over the last few days, and at DigitalOcean we immediately wondered "how can we enable more people to try this new technology safely and easily?" We noticed that there was a lot of interest by folks looking to use this software, but also that there was concern around the security of the open source software, especially when connecting it directly to users' own machines. We dug in to find a way to deliver this software to our customers as fast as possible, as easily as possible and as safe as possible. At DigitalOcean, our 1-Click Deploy OpenClaw (formerly 1-Click Deploy Moltbot) through our Marketplace enables us to package the latest and greatest software configured for our Droplet® server, and make it easily available to customers. Creating our 1-Click Deploy OpenClaw was the natural next step in getting this to our customers. Toying around with OpenClaw on a local machine is fun, but it could severely impact the ability to deploy and use the software for longer term use and may not meet the safe environment that you need. Some of the benefits to deploying on DigitalOcean include: Always available - the service is available to customers via the web Easy to connect to it - Droplets have a static ip address Vertical scalability - scale up CPUs, memory, and disk storage with higher workloads Cognitive overload - start with basic configs, tweak the ones that matter to you We made a lot of changes as we built the 1-Click Deploy OpenClaw, but the main elements we focused on were How do we communicate with the service safely? How do we keep the agentic code isolated from the rest of the system? How do we prevent attacks from the wider internet? All of that while providing a straightforward deployment UX to our customers! Let's dig in... Delivering an Image with Safe Defaults Our priority in creating a 1-Click Deploy OpenClaw on our Droplet was twofold: Fi ## Streamline Your Workflow: Announcing Environment Support for DigitalOcean App Platform DevFeed: [Streamline Your Workflow: Announcing Environment Support for DigitalOcean App Platform]() Original publisher: [Read original article]() Author: Bikram Gupta Published: 2025-11-25T16:06:22Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [App](), [Command-line interface](), [dashboards]() Tags: [announce](), [app](), [apps](), [cli](), [cost](), [digitalocean](), [droplets](), [feature](), [management](), [new-feature](), [organization](), [organizational](), [platform](), [product-updates](), [services](), [workflow]() ### AI overview DigitalOcean announces environment support for App Platform through DigitalOcean Projects, allowing projects to be labeled Development, Staging, or Production and apps to be assigned to them. The article also introduces App Cloning and management through the control panel and CLI. ### Source excerpt As developers, we love building, but we also know that as an application portfolio grows, managing it gets complicated. The line between your production services, your staging environment, and your new feature-branch deployments can blur. Keeping track of which app serves which purpose and quickly identifying all your "production" apps at a glance becomes a significant organizational challenge. We're excited to announce a powerful new way to manage this complexity: Environment Support for DigitalOcean App Platform, powered by DigitalOcean Projects. We're also introducing App Cloning, a new feature to replicate your apps in just a few clicks. This feature allows you to explicitly tag your resource groups (Projects) with a specific environment, such as Development, Staging, or Production and then assign your App Platform apps to those projects. This gives you a high-level, filterable view of your entire application landscape, right from the control panel and via the CLI. The Core Concept The logic is simple but effective: A Project is a "bucket" for your resources. You can group Droplets, Load Balancers, Databases, and App Platform Apps into a single Project. A Project can now be assigned an environment. This flag formally designates that project's purpose. An App Platform App is assigned to a Project. By combining these, you can now associate an app with an environment, enabling clearer organization, better cost management, and more robust scripting and automation. Configuring Environments in the UI You can manage all of this directly from the DigitalOcean Control Panel. When you create a new project (Click "New Project" from the main dashboard), you'll see a new "Environment" dropdown. Here, you can select Development, Staging, or Production to define the project's role. Once your project is created, simply select it during the App Platform app creation wizard. All resources for that app will now be associated with your environment-tagged project. Managing Environme ## GPU Observability: Get Deeper Insights into Your Droplets and DOKS Clusters DevFeed: [GPU Observability: Get Deeper Insights into Your Droplets and DOKS Clusters]() Original publisher: [Read original article]() Author: Waverly Swinton Published: 2025-11-12T20:56:52Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [GPU](), [observability](), [Digital Ocean](), [monitor](), [Artificial Intelligence]() Tags: [ai](), [ai-ml](), [amd](), [clusters](), [data](), [droplets](), [efficiency](), [gpu](), [inference](), [metrics](), [monitor](), [network](), [nvidia](), [observability](), [performance](), [product-updates](), [real-time](), [training]() ### AI overview DigitalOcean introduces basic observability metrics for GPU Droplets and DOKS clusters. The metrics cover GPU utilization, memory, temperature, power consumption, throttling, and interconnect performance, and are available through the DigitalOcean Insights UI. ### Source excerpt We're introducing a new set of basic observability metrics for all GPU Droplets and DOKS clusters, giving you a powerful, simple way to monitor and optimize your AI workloads. Why GPU Observability Matters When running large-scale training, inference, and complex data processing--cluster performance and stability are paramount. Our new observability features are designed to give you the visibility you need to ensure effective utilization of your resources and quickly debug any performance bottlenecks. Get real-time, individual metrics from your NVIDIA and AMD GPUs and their network interfaces on critical factors like utilization, temperature, power consumption, and more--all directly within the DigitalOcean Insights UI, and with zero setup required. What's Included: New Metric Categories We've grouped the new metrics into five intuitive categories to provide a comprehensive view of your GPU and DOKS cluster health and performance: Utilization: Understand how busy your GPU cores and memory are. This includes key metrics like GPU Occupancy and Memory Utilization, allowing you to optimize your setup for peak performance live. Temperature: Monitor thermal conditions to prevent overheating and ensure stable operation under heavy load. Power: Track power consumption, which is essential for understanding GPU performance and efficiency. Throttle: Identify if your GPU is limiting its performance due to thermal, power, or voltage constraints. This is crucial for debugging sudden performance degradations. Interconnect: Gain insights into the network interface performance connecting your GPU resources. Zero Setup, No Extra Cost Observability shouldn't be a hurdle. That's why we've made this feature as seamless as possible: Default on: Observability will be enabled by default the moment you create a GPU Droplet. There is no configuration or effort required on your part. Free: These essential observability metrics are included with the AI/ML Ready images for GPU Droplets. We're com ## Announcing per-sec billing, new Droplet plans, BYOIP, and NAT gateway to reduce scaling costs DevFeed: [Announcing per-sec billing, new Droplet plans, BYOIP, and NAT gateway to reduce scaling costs]() Original publisher: [Read original article]() Author: Nihar Namjoshi Published: 2025-10-02T08:03:13Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [Cloud](), [cloud-infrastructure](), [virtual machines](), [VPC](), [CI/CD]() Tags: [ci-cd](), [cloud](), [cloud-infrastructure](), [digitalocean](), [droplets](), [network](), [product-updates](), [virtual-machines](), [vpc]() ### AI overview DigitalOcean announces per-second billing for Droplets, new dedicated Droplet plans, generally available BYOIP, and a VPC NAT Gateway. The updates target more precise cost control, performance upgrades, IP reputation protection, and centralized egress management. ### Source excerpt To help users cut down on cloud spending that's wasted due to over-provisioning and inflexible billing models, we're introducing tools that offer granular control without sacrificing simplicity or cost-effectiveness. We're excited to announce new product updates that offer granular cost control, improved performance, and a clear path to savings. TL;DR DigitalOcean has transitioned to per-second billing for Droplets. Starting from January 1, 2026, you only pay for the exact compute time you use, perfect for slashing costs on ephemeral tasks and CI/CD pipelines. Create Droplets for short-lived workloads. New dedicated Droplet plans are now generally available for a seamless performance upgrade. Visit your DigitalOcean console to create these new Droplets. Bring your own IP is now generally available to protect your IP reputation. Check out our documentation or visit your DigitalOcean console to bring your own ip. VPC NAT gateway is now generally available for centralized egress and static IPs. Join our webinar: Stop the manual struggle of managing NAT instances and bastion hosts or check out our documentation or visit your DigitalOcean console to set up your NAT gateway. Droplets per-second billing slashes costs for ephemeral workloads Traditional hourly billing models for virtual machines have resulted in customers paying for idle time, even for short-lived workloads. Starting from Jan 1, 2026, our billing model transitioned to a per-second basis for Droplets, with a minimum charge of 60 seconds or $0.01, whichever is higher. This new approach aims to optimize cost control by charging for exact usage over a minute, making it simple to get precise billing for your actual usage. For sustained workloads, the monthly cap of 672 hours (24 hours x 28 days) of usage remains in place, ensuring your bill never exceeds the predictable monthly price. Imagine your development team uses a CI/CD pipeline that uses $84/month CPU-Optimized Droplet to run automated tests taking 10 mi