Training Example: DigitalOcean – Review the Data, Give Your Score & Compare to the Real AI Evaluation

[H1] AI-Native Cloud
One platform, fully integrated from silicon to agent, with economics that improve as you scale.Get StartedExplore products255010020030040050060070080090010001100120013001400
[H2]
From real-time agents to trillion-token workloads, leaders in AI run on DigitalOcean.
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[H3] 67%
lower costWorkato runs 1T+ automation tasks on DigitalOcean's Inference Engine at 67% lower cost — with 67% higher throughput on the same workload.
[IMG: Workato]
Learn more
[H3] 2x
inference throughputCharacter.ai handles 1B+ queries per day with 2× production inference throughput on DigitalOcean's AMD Instinct™ GPUs.
[IMG: Character.ai]
Learn more
[H3] 40%
reduction in latencyHippocratic AI runs healthcare agents on DigitalOcean, powering 20M+ patient interactions with 40% lower end-to-end P99 latency and 2× higher throughput.
[IMG: Hippocratic AI]
Learn more
[H2] Five layers. One platform. Open at every layer.
From GPUs to agent runtimes, every layer purpose-built for production AI and integrated end-to-end. Most clouds only cover one or two layers, or fragment all five across 300+ disconnected services.Managed AgentsData & LearningInference EngineCore CloudInfrastructure
[H2] Managed Agents
Production agents that run on the same stack as your data, inference, and infrastructure. No cross-vendor hops. No lost context. No egress fees between layers.ProductsOpen HarnessSandboxPlanoToolboxStateOpen Source IntegrationsOpen agent orchestration: OpenCode, LangGraph, CrewAI, MCP / A2A, E2B, Daytona
[H2] Data & Learning
Fresh data, persistent memory, and continuous learning, without rebuilding your data stack.ProductsKnowledge BasesManaged DatabasesAnalytics EngineOpen Source IntegrationsOpen retrieval and embedding including pgvector, Qdrant APIs, LlamaIndex, Chroma, PostgreSQL, MySQL, Valkey
[H2] Inference Engine
Over 70 models, open-weighted and frontier, on one endpoint. Run serverless, dedicated, or batch inference, with the Inference Router optimizing every call.ProductsInference Router (Public preview)Serverless InferenceDedicated InferenceBatch Inference72 Models or Bring Your Own ModelEvaluations (Public preview)Open Source IntegrationsOpen models and serving: DeepSeek V3.2, Qwen 3, vLLM, Firecracker
[H2] Core Cloud
The cloud millions already run on, with the primitives every AI workload needs.ProductsDroplets (CPU & GPU)Managed KubernetesApp PlatformNetworkingStorage & BackupsFunctionsOpen Source IntegrationsOpen infrastructure orchestration: Kubernetes, Cilium, MinIO
[H2] Infrastructure
We own the silicon. Your unit economics improve as you scale.Products20 data centers across 11 regionsAir-cooled and liquid-cooled infrastructureNVIDIA H100 / H200 / BlackwellAMD Instinct™ MI300X / MI325X / MI350X400G RoCE fabricOpen Source IntegrationsOpen monitoring and compute: Prometheus, Grafana, Ollama, Linux / KVMBrowse all products
[H2] Performance, economics, and simplicity — together.
[H2] Performance proven in production
Sub-second Time-to-First-Token (TTFT). 3.9× higher output speed vs. AWS Bedrock. The most consistent latency across context lengths of any provider tested. Independently benchmarked by Artificial Analysis on DeepSeek V3.2.
[H2] Open models you already trust
DeepSeek, Llama, Qwen — plus frontier labs and your own fine-tunes — on one OpenAI-compatible endpoint. DigitalOcean Inference Router picks the right model per call, automatically. Your code doesn't change when a better model ships.
[H2] Built for how builders ship
One CLI. One API. One bill. Migrate in one line of code, and leave on the same terms. The complexity of stitching together multiple vendors — gone.
[H2] Economics that compound as you scale
DigitalOcean owns the silicon, the fabric, and the Inference Engine end-to-end. Every optimization below the line passes forward automatically. Performance and unit economics improve together.
[H2] Resources
View allPreviousNextTutorial
[H3] Build a Cost-Aware AI Support Triage API using Serverless Inference via Inference Router
May 14, 202617 min readReadBlog
[H3] Your Model Doesn't Matter. Your Infrastructure Does.
May 13, 20267 min readReadTutorial
[H3] Inference Routing: Matching Models to Tasks, Not Just Requests
May 13, 202622 min readReadTutorial
[H3] AI Now Tells you if a Meeting could be an Email
May 12, 202610 min readReadTutorial
[H3] How to Run Hermes Agent with DigitalOcean
May 12, 20269 min readReadTutorial
[H3] Hermes Agent on DigitalOcean Serverless Inference
May 11, 202613 min readReadArticle
[H3] AI Security: 10 Top Risks and Best Practices in 2026
May 8, 202616 min readReadArticle
[H3] 10 AI Inference Platforms for Production Workloads in 2026
May 8, 202620 min readReadTutorial
[H3] Long-Context Inference at Scale: The Hidden Infrastructure Cost
May 8, 202614 min readRead
[H2] Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign up

[H1] Tutorials
Follow along with one of our 8,000+ development and sysadmin tutorials.To add a tag to the search, type the tag with [ ] around it. Or, search this query on [questions and answers].Popular Topics
[H2] Featured content
[IMG: SOLID Design Principles Explained: Building Better Software Architecture]
Conceptual Article
[H3] SOLID Design Principles Explained: Building Better Software Architecture
June 12, 2025View Conceptual Article
[IMG: How To Remove Docker Images, Containers, and Volumes]
Tutorial
[H3] How To Remove Docker Images, Containers, and Volumes
January 29, 2026View Tutorial
[IMG: How to Create a MySQL User and Grant Privileges (Step-by-Step)]
Tutorial
[H3] How to Create a MySQL User and Grant Privileges (Step-by-Step)
January 23, 2026View Tutorial
[H2] Results
FiltersTopic tagAll topicsContent typeAll ContentSort byNewestAddedAll TimeLanguageEnglishApply FiltersClear FiltersTutorial
[H3] Build a Cost-Aware AI Support Triage API using Serverless Inference via Inference Router
May 14, 2026View TutorialTutorial
[H3] Inference Routing: Matching Models to Tasks, Not Just Requests
May 13, 2026View TutorialTutorial
[H3] AI Now Tells you if a Meeting could be an Email
May 12, 2026View TutorialTutorial
[H3] Nginx Rewrite URL Rules: Examples and Configuration
May 12, 2026View TutorialTutorial
[H3] Use Ansible to Install Docker on Ubuntu
May 12, 2026View TutorialTutorial
[H3] How To Use AWK to Manipulate Text in Linux
May 12, 2026View TutorialTutorial
[H3] Set Up Squid Proxy on Ubuntu: Complete Guide
May 12, 2026View TutorialTutorial
[H3] How to Run Hermes Agent with DigitalOcean
May 12, 2026View TutorialTutorial
[H3] How To Target Your Users with Nginx Analytics and A/B Testing
May 11, 2026View TutorialTopicsAll topics tagsStart building todayFrom GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign upFiltersTopic tagAll topicsContent typeAll ContentSort byNewestAddedAll TimeLanguageEnglishApply FiltersClear Filters
[H2] The developer cloud
Scale up as you grow — whether you're running one virtual machine or ten thousand.View all products
[H2] Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign upDark mode is coming soon.

[H1] Every product for production AI, on one cloud
Explore the full AI-Native Cloud, from GPUs and silicon to inference, data, and agents, with economics that improve as you scale.Contact salesGet started
[H2] From silicon to agent, DigitalOcean has every layer you need to build and scale AI.
[H3] Managed Agents
Production agents that run on the same stack as your data, inference, and infrastructure. No cross-vendor hops. No lost context. No egress fees between layers.Learn More
[H3] Data & Learning
Fresh data, persistent memory, and continuous learning, without rebuilding your data stack.Learn More
[H3] Inference Engine
Over 70 models, open-weighted and frontier, on one endpoint. Run serverless, dedicated, or batch inference, with the Inference Router optimizing every call.Learn More
[H3] Core Cloud
The cloud millions already run on, with the primitives every AI workload needs.Learn More
[H3] Data Center Infrastructure
We own the silicon. Your unit economics improve as you scale.Learn More
[IMG: Ace Studio logo]
Sometimes we need to scale up, but hyperscalers don't have any GPUs left. The low-cost local data centers have fragile reliability and stability. We were looking for a provider like DigitalOcean that sat between these two options, which had availability but also reliability at scale.
[IMG: Sean Zhao]
Sean ZhaoACE Studio, Co-Founder
[H2] Managed Agents
[H3] Launchpad
Go from idea to a production-ready application in as little as minutes with fully configured starter kits for RAG assistants, data pipelines, and observability. No infrastructure expertise required.Go to Launchpad
[H3] Functions
A serverless computing solution that runs on-demand, enabling you to focus on your code, scale instantly with confidence, and save costs by eliminating the need to maintain servers.Go to Functions
[H2] Data & Learning
Learn More
[H3] Managed Databases
Worry-free database hosting. Leave the complexity of database administration to us. We'll handle setting up, backing up with Point-in-Time Recovery (PITR), and updating so you can focus on building great apps.Try it today
[H3] Knowledge Bases
Fully managed Retrieval-Augmented Generation (RAG) service that enables developers to build, test, and deploy AI-powered search and Q&A applications without managing embedding infrastructure, vector databases, or retrieval logic.Try it today
[H3] Managed Weaviate (Private Preview)
Production-ready vector infrastructure for AI apps with 1-click provisioning and predictable pricing, starting at just $20/month.Try it today
[H2] Inference Engine
Learn More
[H3] Inference Router (Public Preview)
Policy-driven control replaces manual routing logic and adapts in real time. Teams define routing behavior using natural language or structured rules to optimize for cost, latency, and reliability without hardcoding models.Go to Inference Router
[H3] Model Evaluations (Public Preview)
Structured testing enables validation of catalog, Bring Your Own Model (BYOM), and inference routers using real datasets before production deployment. LLM-as-a-judge evaluates quality, latency, cost, and safety, with a unified dashboard to compare results and re-run evaluations as models evolve.Go to Model Evaluations
[H3] Model Playground
A unified playground enables experimentation across text, image, audio, and video models in a single interface. Side-by-side testing, real-time inference, and exportable production-ready API code support rapid transition from experimentation to implementation.Go to Model Playground
[H3] Dedicated Inference
Controlled, high-performance model hosting supports sustained production workloads with dedicated infrastructure. Dedicated GPU endpoints, BYOM support, and configurable scaling and performance settings enable production-grade control without Kubernetes complexity.Go to Dedicated Inference
[H3] Serverless Inference
Real-time AI inference supports applications, APIs, and agents through a unified system. The platform provides access to 70+ models with multimodal generation, intelligent routing for cost and latency optimization, and built-in observability for production workloads.Go to Serverless Inference
[H3] Batch Inference
Large-scale asynchronous workloads run through job-based inference designed for non-real-time use cases. Batch processing includes up to 50% cost savings and support for evaluation, enrichment, and moderation pipelines.Go to Batch Inference
[H3] 1-Click Models
Deploy popular AI models from providers like Hugging Face and DeepSeek on GPU Droplets with just a single click.Go to 1-Click Models
[H3] Content Safety Guardrails
Always-on input and output content evaluation built into every inference request, applying policy-based allow/flag/block decisions to help support compliance needs with AI-generated content.Go to Content Safety Guardrails
[H3] Model Catalog
A single pane of glass across every model on the platform with side-by-side evaluation, benchmark comparison, and one-click deployment, with day-zero availability of select new models as they ship.Go to Model Catalog
[H2] Core Cloud
[H3] Droplets
On-demand Linux virtual machines. Choose from shared CPU and dedicated CPU plans, with variable amounts of RAM, locally attached SSD storage, and generous transfer quotas.Go to Droplets
[H3] GPU Droplets
Simple, affordable, and flexible virtual GPUs from NVIDIA and AMD, designed to reliably run training and inference on AI/ML workloads and to process large datasets and complex neural networks.Go to GPU Droplets
[H3] Bare Metal GPUs
Support complex and custom AI/ML use cases for your most demanding workloads.Go to Bare Metal GPUs
[H3] App Platform
Build, deploy, and scale apps quickly using a simple, fully managed solution. We'll handle the infrastructure, app runtimes and dependencies, so you can focus on your code.Go to App Platform
[H3] Kubernetes
An easy-to-use managed Kubernetes service for both GPU and CPU workloads, providing you uptime, scalability, and portability for your cloud native apps. Free control plane included.Go to Kubernetes
[H3] Network
Secure, isolate, and scale application traffic with built-in networking primitives including VPCs, load balancing, firewalls, Private IP and hybrid connectivity.Go to Network
[H3] Storage
Store and access any amount of data reliably in the cloud, with S3-compatible Spaces Object Storage, network-based Volumes block storage, or NFS-based Network File Storage.Go to Storage
[H3] Container & Images
Create and manage compute environments with flexible images, including prebuilt distributions, 1-Click apps, snapshots, backups, and custom images.Go to Container & Images
[H3] Security
Protect infrastructure with identity controls, posture management, and built-in DDoS protection to keep cloud environments secure and resilient.Go to Security
[H3] Backups & Snapshots
Protect your Droplet data with automated daily* backups and Augment your data backups with on-demand images of Droplets.Go to Backups
[H2] Data Center Infrastructure
[H3] Global infrastructure
Deliver applications globally with a resilient, distributed infrastructure spanning 20 data centers across 11 global regions.Go to Global Infrastructure
[H2] Still have questions?
Have a complex setup or additional questions around pricing? Contact our sales team to get more information on DigitalOcean pricing.Contact sales
[H2] Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign up

[H1] The DigitalOcean Blog
Dive into DigitalOcean product updates, company news, and educational content on how developers and startups can leverage the cloud.
[IMG: Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud]
Product updates
[H3] Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud
Vinay Kumar, Chief Product & Technology OfficerMay 4, 20267 min readRead more
[H2] Category topics
Product updatesCommunityCultureCloud educationEngineeringTrust & SecurityNewsPartner NewsSign up now and you'll be up and running on DigitalOcean in just minutes.Get started
[H2] Stay up to date, sign up for our newsletter
New accounts only. By submitting your email you agree to our Privacy Policy
[H2] Latest posts
[IMG: Your Model Doesn]
Engineering
[H3] Your Model Doesn't Matter. Your Infrastructure Does.
adagoneseMay 13, 20267 min readRead more
[IMG: Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud]
Product updates
[H3] Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud
Vinay Kumar, Chief Product & Technology OfficerMay 4, 20267 min readRead more
[IMG: Introducing DigitalOcean AI-Native Cloud for Production AI Workloads]
Product updates
[H3] Introducing DigitalOcean AI-Native Cloud for Production AI Workloads
Paddy SrinivasanApril 28, 20264 min readRead more
[H2] Product updates
View allPreviousNext
[IMG: Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud]
[H3] Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud
Vinay Kumar, Chief Product & Technology OfficerMay 4, 20267 min readRead more
[IMG: Introducing DigitalOcean AI-Native Cloud for Production AI Workloads]
[H3] Introducing DigitalOcean AI-Native Cloud for Production AI Workloads
Paddy SrinivasanApril 28, 20264 min readRead more
[IMG: The Agentic Era Demands a New Class of Infrastructure: DigitalOcean Acquires Katanemo Labs]
[H3] The Agentic Era Demands a New Class of Infrastructure: DigitalOcean Acquires Katanemo Labs
Vinay Kumar, DigitalOcean Chief Product & Technology OfficerApril 2, 20263 min readRead more
[IMG: Run Advanced Reasoning on DigitalOcean with Arcee AI]
[H3] Run Advanced Reasoning on DigitalOcean with Arcee AI's Trinity Large-Thinking
DigitalOceanApril 1, 20263 min readRead more
[IMG: Now Available: DigitalOcean Cloud Security Posture Management (CSPM)]
[H3] Now Available: DigitalOcean Cloud Security Posture Management (CSPM)
Grace MorganApril 1, 20262 min readRead more
[IMG: NVIDIA GTC 2026 Confirmed It: The Inference Era Is Here]
[H3] NVIDIA GTC 2026 Confirmed It: The Inference Era Is Here
Meghan GradyMarch 27, 20263 min readRead more
[IMG: Meet the New Standard for High-Performance, Low-Cost Inference: NVIDIA Dynamo 1.0 is now available to DigitalOcean Customers]
[H3] Meet the New Standard for High-Performance, Low-Cost Inference: NVIDIA Dynamo 1.0 is now available to DigitalOcean Customers
Waverly SwintonMarch 19, 20263 min readRead more
[IMG: DigitalOcean at NVIDIA GTC 2026: Building the AI Factory for the Agentic Era]
[H3] DigitalOcean at NVIDIA GTC 2026: Building the AI Factory for the Agentic Era
Vinay Kumar, DigitalOcean Chief Product & Technology OfficerMarch 16, 20263 min readRead more
[IMG: Deploy Smarter with AI: Introducing App Platform Skills on DigitalOcean]
[H3] Deploy Smarter with AI: Introducing App Platform Skills on DigitalOcean
Bikram GuptaMarch 16, 20267 min readRead more
[H2] Community
View allPreviousNext
[IMG: Heroku’s Next Chapter Is Maintenance. Yours Shouldn’t Be]
[H3] Heroku’s Next Chapter Is Maintenance. Yours Shouldn’t Be
Wade WegnerFebruary 9, 20265 min readRead more
[IMG: Powered by DigitalOcean Hatch: How Ex-human uses GPU Droplets to Build Empathetic AI that Serves Customers]
[H3] Powered by DigitalOcean Hatch: How Ex-human uses GPU Droplets to Build Empathetic AI that Serves Customers
Martin NguyenNovember 21, 20253 min readRead more
[IMG: Hacktoberfest 2025 Comes to a Close]
[H3] Hacktoberfest 2025 Comes to a Close
Haimantika MitraNovember 21, 20254 min readRead more
[IMG: Hacktoberfest 2025: How to Participate]
[H3] Hacktoberfest 2025: How to Participate
Haimantika MitraSeptember 29, 20253 min readRead more
[IMG: Hacktoberfest 2025: Celebrate All Things Open Source!]
[H3] Hacktoberfest 2025: Celebrate All Things Open Source!
DigitalOceanSeptember 19, 20253 min readRead more
[IMG: Stop Building SaaS from Scratch: Meet the SeaNotes Starter Kit]
[H3] Stop Building SaaS from Scratch: Meet the SeaNotes Starter Kit
Amit JotwaniAugust 21, 20253 min readRead more
[IMG: Powered by DigitalOcean Hatch: Why Uxify’s Founders Always Choose DigitalOcean]
[H3] Powered by DigitalOcean Hatch: Why Uxify’s Founders Always Choose DigitalOcean
Martin NguyenJuly 10, 20254 min readRead more
[IMG: Powered by DigitalOcean Hatch: Ontra Mobility is Building Smarter Cities]
[H3] Powered by DigitalOcean Hatch: Ontra Mobility is Building Smarter Cities
Martin NguyenMay 7, 20254 min readRead more
[IMG: DigitalOcean Hatch: Accelerate your AI/ML startup with exclusive GPU offerings and benefits]
[H3] DigitalOcean Hatch: Accelerate your AI/ML startup with exclusive GPU offerings and benefits
Krystal FernandezNovember 26, 20243 min readRead more
[H2] Culture
View allPreviousNext
[IMG: DigitalOcean India: Inside Our Growing Hub for AI and Cloud Innovation]
[H3] DigitalOcean India: Inside Our Growing Hub for AI and Cloud Innovation
Sujatha RMarch 24, 20264 min readRead more
[IMG: Zero to Deploy: Launching Your Career at DigitalOcean]
[H3] Zero to Deploy: Launching Your Career at DigitalOcean
Sujatha RFebruary 25, 20263 min readRead more
[IMG: Unstoppable Velocity: Why 2026 is the Year to Join DigitalOcean]
[H3] Unstoppable Velocity: Why 2026 is the Year to Join DigitalOcean
ccarpenterJanuary 6, 20262 min readRead more
[IMG: From User to Trusted Advisor: How Jeff Fan Powers Customer Success at DigitalOcean]
[H3] From User to Trusted Advisor: How Jeff Fan Powers Customer Success at DigitalOcean
Sujatha RDecember 8, 20253 min readRead more
[IMG: Leading the Cloud With Curiosity : Spotlight on Pranav Nambiar, SVP, AI/ML & PaaS]
[H3] Leading the Cloud With Curiosity : Spotlight on Pranav Nambiar, SVP, AI/ML & PaaS
Sujatha RNovember 4, 20253 min readRead more
[IMG: Is DigitalOcean Your Next Career Spot? A 5-Year Insider on Why It Should Be]
[H3] Is DigitalOcean Your Next Career Spot? A 5-Year Insider on Why It Should Be
Sujatha ROctober 9, 20252 min readRead more
[IMG: Sharks of DigitalOcean: Archana Kamath, Senior Director, IaaS]
[H3] Sharks of DigitalOcean: Archana Kamath, Senior Director, IaaS
Sujatha RSeptember 3, 20253 min readRead more
[IMG: Sharks of DigitalOcean: Darian Wilkin, Senior Manager, Solutions Engineering]
[H3] Sharks of DigitalOcean: Darian Wilkin, Senior Manager, Solutions Engineering
Sujatha RAugust 14, 20253 min readRead more
[IMG: Sharks of DigitalOcean: Laura Schaffer, VP, Growth]
[H3] Sharks of DigitalOcean: Laura Schaffer, VP, Growth
Sujatha RJuly 10, 20252 min readRead more
[H2] Cloud education
View allPreviousNext
[IMG: Introducing langchain-gradient: Seamless LangChain Integration with DigitalOcean Gradient™ AI Platform]
[H3] Introducing langchain-gradient: Seamless LangChain Integration with DigitalOcean Gradient™ AI Platform
Narasimha BadrinathAugust 19, 20252 min readRead more
[IMG: Agentic Cloud: Reinventing the Cloud with AI Agents]
[H3] Agentic Cloud: Reinventing the Cloud with AI Agents
Bratin Saha, Chief Product & Technology OfficerMay 19, 20255 min readRead more
[IMG: How to optimize your cloud architecture for business growth]
[H3] How to optimize your cloud architecture for business growth
Anantha RamachandranMay 9, 20255 min readRead more
[IMG: Choosing the Right DigitalOcean Offering for Your AI/ML Workload]
[H3] Choosing the Right DigitalOcean Offering for Your AI/ML Workload
Grace MorganNovember 25, 20245 min readRead more
[IMG: Top 10 Reasons to Choose DigitalOcean’s Managed Kafka Solution]
[H3] Top 10 Reasons to Choose DigitalOcean’s Managed Kafka Solution
Faye HutsellApril 23, 20244 min readRead more
[IMG: Accelerate Your Business with DigitalOcean App Platform]
[H3] Accelerate Your Business with DigitalOcean App Platform
Bikram GuptaApril 1, 20245 min readRead more
[IMG: Access the New Cloud Buying Criteria Proposed by IDC for 2024]
[H3] Access the New Cloud Buying Criteria Proposed by IDC for 2024
Faye HutsellMarch 27, 20243 min readRead more
[IMG: How ISVs and startups scale on DigitalOcean Kubernetes: Best Practices Part II - Observability]
[H3] How ISVs and startups scale on DigitalOcean Kubernetes: Best Practices Part II - Observability
Bikram GuptaMarch 21, 202413 min readRead more
[IMG: How ISVs and startups scale on DigitalOcean Kubernetes: Best practices for DOKS adoption]
[H3] How ISVs and startups scale on DigitalOcean Kubernetes: Best practices for DOKS adoption
Bikram GuptaFebruary 26, 202410 min readRead more
[H2] Engineering
View allPreviousNext
[IMG: Your Model Doesn]
[H3] Your Model Doesn't Matter. Your Infrastructure Does.
adagoneseMay 13, 20267 min readRead more
[IMG: How we built the most performant DeepSeek V3.2, MiniMax-M2.5 and Qwen 3.5 397B on DigitalOcean Serverless Inference]
[H3] How we built the most performant DeepSeek V3.2, MiniMax-M2.5 and Qwen 3.5 397B on DigitalOcean Serverless Inference
Debarshi RahaApril 28, 20266 min readRead more
[IMG: DigitalOcean Dedicated Inference: A Technical Deep Dive]
[H3] DigitalOcean Dedicated Inference: A Technical Deep Dive
dguptaApril 25, 20266 min readRead more
[IMG: Beyond the Abyss Project Poseidon’s Quest for Zero-Downtime Reliability]
[H3] Beyond the Abyss Project Poseidon’s Quest for Zero-Downtime Reliability
Sartaj BhuvajiApril 23, 20267 min readRead more
[IMG: From Incident Counting to SLIs: How DigitalOcean Rethought Availability]
[H3] From Incident Counting to SLIs: How DigitalOcean Rethought Availability
Miguel CarreraApril 23, 202611 min readRead more
[IMG: The LLM Inference Trilemma: Throughput, Latency, Cost]
[H3] The LLM Inference Trilemma: Throughput, Latency, Cost
Balaji VaradarajanApril 22, 202612 min readRead more
[IMG: Mastering the 600B+ Frontier: Optimizing Large Model Deployments on the Inference Cloud]
[H3] Mastering the 600B+ Frontier: Optimizing Large Model Deployments on the Inference Cloud
Brett SnyderApril 21, 20269 min readRead more
[IMG: The Inference Cloud Memory Layer: A Technical Dive into DigitalOcean Managed Databases]
[H3] The Inference Cloud Memory Layer: A Technical Dive into DigitalOcean Managed Databases
Joe KeeganApril 17, 202610 min readRead more
[IMG: Load Balancing and Scaling LLM Serving]
[H3] Load Balancing and Scaling LLM Serving
Mohammad Ashar KhanApril 15, 20267 min readRead more
[H2] Trust & Security
View allPreviousNext
[IMG: Enhancing Security with User-Specific Access Keys for DigitalOcean Functions]
[H3] Enhancing Security with User-Specific Access Keys for DigitalOcean Functions
Amulya TomerMarch 23, 20265 min readRead more
[IMG: OAuth App Based Workload Identity for Droplets]
[H3] OAuth App Based Workload Identity for Droplets
John AndersenOctober 22, 20258 min readRead more
[IMG: How DigitalOcean Uses Semgrep to Fortify Security: A Highlight From Our Toolset]
[H3] How DigitalOcean Uses Semgrep to Fortify Security: A Highlight From Our Toolset
Jordan VaughnOctober 7, 20242 min readRead more
[IMG: Contextual Vulnerability Management With Security Risk As Debt]
[H3] Contextual Vulnerability Management With Security Risk As Debt
Ari KalfusAugust 12, 202413 min readRead more
[IMG: Regresshion vulnerability: Recommended actions and steps we]
[H3] Regresshion vulnerability: Recommended actions and steps we've taken
July 2, 20247 min readRead more
[IMG: DigitalOcean and HIPAA: Enabling Healthcare Innovation on our Platform]
[H3] DigitalOcean and HIPAA: Enabling Healthcare Innovation on our Platform
David LopezJuly 1, 20242 min readRead more
[IMG: Announcing the Public Launch of DigitalOcean’s Paid Bug Bounty Program]
[H3] Announcing the Public Launch of DigitalOcean’s Paid Bug Bounty Program
Ari KalfusApril 5, 20244 min readRead more
[IMG: Fine-Grained RBAC For GitHub Action Workflows With GitHub OIDC and HashiCorp Vault]
[H3] Fine-Grained RBAC For GitHub Action Workflows With GitHub OIDC and HashiCorp Vault
Ari KalfusFebruary 3, 202328 min readRead more
[IMG: Enabling Engineering Teams Through Developer-First Secrets Management]
[H3] Enabling Engineering Teams Through Developer-First Secrets Management
Ari KalfusJanuary 26, 20238 min readRead more
[H2] News
View allPreviousNext
[IMG: Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai]
[H3] Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai
Piyush SrivastavaJanuary 13, 202613 min readRead more
[IMG: Currents Report: How Growing Tech Businesses Use AI Today]
[H3] Currents Report: How Growing Tech Businesses Use AI Today
Roxie ElliottFebruary 6, 20253 min readRead more
[IMG: Introducing the DigitalOcean Netlify Extension]
[H3] Introducing the DigitalOcean Netlify Extension
Quinn EckartOctober 3, 20242 min readRead more
[IMG: Join us at Deploy, DigitalOcean’s virtual conference]
[H3] Join us at Deploy, DigitalOcean’s virtual conference
DigitalOceanMay 28, 20242 min readRead more
[IMG: Driving Inclusive Entrepreneurship with DO Impact]
[H3] Driving Inclusive Entrepreneurship with DO Impact
Admas KanyagiaFebruary 12, 20244 min readRead more
[IMG: Turbocharge Your Business with a Black Friday Cyber Monday Deal from Cloudways]
[H3] Turbocharge Your Business with a Black Friday Cyber Monday Deal from Cloudways
DigitalOceanNovember 21, 20234 min readRead more
[IMG: Paperspace Joins DigitalOcean to Expand AI Capabilities]
[H3] Paperspace Joins DigitalOcean to Expand AI Capabilities
Yancey SpruillJuly 6, 20233 min readRead more
[IMG: DigitalOcean launches Partner Directory]
[H3] DigitalOcean launches Partner Directory
DigitalOceanMay 22, 20232 min readRead more
[IMG: DigitalOcean expands backup capabilities with acquisition of SnapShooter]
[H3] DigitalOcean expands backup capabilities with acquisition of SnapShooter
Gabe MonroyJanuary 11, 20233 min readRead more
[H2] Partner News
View allPreviousNext
[IMG: DigitalOcean and ProxySQL LLC Collaborate to Bring PROXY Protocol Support to ProxySQL]
[H3] DigitalOcean and ProxySQL LLC Collaborate to Bring PROXY Protocol Support to ProxySQL
Charles ThompsonOctober 10, 20243 min readRead more
[IMG: DigitalOcean Monthly Partnership Roundup August and September, 2024]
[H3] DigitalOcean Monthly Partnership Roundup August and September, 2024
DigitalOceanOctober 4, 20242 min readRead more
[IMG: July 2024 Partnership Roundup]
[H3] July 2024 Partnership Roundup
DigitalOceanJuly 30, 20242 min readRead more
[IMG: June 2024 Partnership Roundup]
[H3] June 2024 Partnership Roundup
DigitalOceanJune 28, 20242 min readRead more
[IMG: Jumpstart your growth with

[H1] DigitalOcean inference cloud solutions
Find the just-right solution for your specific build. From GPU-powered virtual machines for AI projects to affordable hosting for the most popular web apps online, DigitalOcean offers digital native enterprises every infrastructure-as-a-service tool they need to quickly set up robust cloud infrastructure and get back to scaling their business.
[H2] AI, GPUs, high performance, and data
Access lightning-fast GPUs for every use case, secure streaming infrastructure, and deploy DigitalOcean AI for inferencing and much more.AIGPUsBuild the future of AI with powerful tools ready to deploy AI cloud infrastructure today.AI agent builderAI coding copilotAI knowledge assistant for HRAI recommendation engineAI support ticket triageLLM applicationsMultimodal AIAI GPU hostingClick on one of the items above to learn moreRun your AI/ML projects on ultra-reliable, ultra-powerful GPUs from NVIDIA and AMD.GPUs for LLMsNVIDIA H100 GPUsGPUs for AI trainingLow-latency inferenceGPU inferenceHigh-performance computingGPU clustersGPU fine tuningGPU cloud platformMulti GPUClick on one of the items above to learn more
[H2] Cloud infrastructure and global reach
Flexible compute options together with powerful digital infrastructure tools for digital native enterprises.
[H2] Cloud hosting
Quickly stand up reliable infrastructure and website hosting and VPS hosting.
[H3] VPS hosting
Learn more
[H3] Website hosting
Learn more
[H3] Virtual machines
Learn more
[H3] Linux hosting
Learn more
[H2] Networking and security
Help ensure your infrastructure is reliable and secure with powerful cloud security solutions.
[H3] VPN
Learn more
[H3] Web hosting security
Learn more
[H3] FTP hosting
Learn more
[H2] Global hosting
Host your app from anywhere in the world with reliable digital infrastructure that just works.Infrastructure across the world
[H2] DevOps and App development
Build, deploy, and manage your apps easily with simple, effective hosting for everything that keeps your app up and running.Web and ApplicationsDeveloper Tools and WorkflowsBuild your apps with the tools you know and love, including powerful container orchestration.DockerNode.jsBuild and run apps for mobilecPanelNext.jsLAMPClick on one of the items above to learn moreDeploy your apps without altering the workflow that works for you, including CI/CD pipelines.Developer toolsCICD pipelinesGit hostingGitLab hostingClick on one of the items above to learn more
[H2] CMS and Framework Hosting
Get your content up with some of the most simple, powerful CMS options around, including WordPress hosting.
[H3] Wordpress hosting
Learn more
[H3] Laravel hosting
Learn more
[H3] Content hosting
Learn more
[H3] Magento hosting
Learn more
[H3] Drupal hosting
Learn more
[H3] Ghost hosting
Learn more
[H3] Joomla hosting
Learn more
[H2] Inference Cloud solutions by use case
Business and Agency SolutionsOnline StoresWeb3 and Emerging TechRun and grow your business with cloud infrastructure that just works.Startups of all sizesSmall businessesDigital Marketing agenciesFreelance website hostersConsultingClick on one of the items above to learn moreRun your online e-commerce shop on robust digital infrastructure you can trust.E-commerce hostingDropshipping hostingClick on one of the items above to learn moreBuild with cutting-edge Web3 infrastructure and blockchain hosting.BlockchainInternet of Things (IoT) cloudISVs and contractorsClick on one of the items above to learn more
[H2] Streaming and gaming
Host your own gaming servers and more.
[H3] Streaming on DigitalOcean
Learn more
[H3] Gaming development
Learn more
[H3] Hosting for Minecraft servers
Learn more
[H2] Data and martech
Process and analyze huge amounts of data reliably and quickly.
[H3] Data analytics
Learn more
[H3] Hosting for data streaming
Learn more
[H3] Managed website hosting for Martech
Learn more
[H2] Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign up

[H1] Simple, predictable pricing
Always know what you'll pay with monthly caps and flat pricing.Get Started
[H2] Enterprise-grade infrastructure trusted by 600k+ customers running AI inference, serving thousands of requests, and executing every big idea in between.
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[IMG: AmorphousData]
[IMG: character.ai]
[IMG: Ace Studio]
[IMG: Hippocratic AI]
[IMG: Ideogram]
[IMG: Workato]
[IMG: Fal.ai]
[IMG: Traversal]
[H2] Choose the cloud solutions you need—or get an assist from our experts
Get help from our sales team
[H2] AI/ML
[H3] AI Platform
Starting at$0.05/M tokensSimplified AI agent creation and LLM integrationCreate custom AI AgentsIntegrate leading LLMs into your workflowsNo infrastructure managementView AI Platform pricing
[H3] GPU Droplets
Starting at$1.88/GPU/hour**Based on multi-month contractual commitment.On-demand pricing from $0.76/GPU/hour.Scalable machines for your AI/ML workloads.Run training and inference on AI/ML modelsProcess large data sets and complex neural networksServe additional use cases like high-performance computing (HPC)View GPU Droplets pricing
[H3] Additional GPU Options
Prices varyExplore more GPU compute options for every purpose.Simple provisioning interfaceBuild, train, and deploy large modelsScale AI/ML workloads on demandView additional GPUs pricing
[H2] Compute
[H3] App Platform
Starting at$0/monthSimple, fully-managed infrastructure solutionBuild, deploy and scale apps quicklyFully managed solution, zero infrastructure managementHighly scalableView App Platform pricing
[H3] Droplets
Starting at$4/monthHighly-efficient virtual machinesPer-sec billing with 60 sec minimum or $0.01, whichever is higherDeploy in secondsScale up on demandRun any workload - from mission critical apps to low-traffic sitesView Droplet pricing
[H3] Kubernetes
Starting at$12/monthSimple, managed KubernetesSimple, managed Kubernetes built for scaleFree control plane, free bandwidth allowance, and moreAutomate and optimize to peak performanceView Kubernetes pricing
[H3] Functions
Starting at$0/monthServerless computing solutionFocus on building great appsPay for what you useScale automaticallyView Functions pricing
[H3] Cloudways Managed Hosting
Starting at$11/monthScalable, pay-as-you-go hosting for digital businessesOptimized for Wordpress & PHP based appsSSD stack with PHP 8 & RedisUnlimited apps, Git & stagingView pricing
[H2] Database & Backups
[H3] Backups
Percentage-based20%(for weekly) of Droplet cost per month30%(for daily) of Droplet cost per monthUsage-based starting at$0.01/GiB per monthProtect your business data with flexible and automated backup plans.Choose flexible frequencies  from Weekly, Daily, or Every 12/6/4 hours.Set custom retention periods from 3 days up to 6 months.Fast and fully-automated.View Backups pricing
[H3] Databases
Starting at$15/monthFully managed and maintainedManaged MongoDB, Kafka, PostgreSQL, MySQL, Caching, Valkey, and OpenSearchWorry-free setup, maintenance, and easy migration Free daily backups, automated failover, and more!View Managed Database pricing
[H2] Storage
[H3] Spaces
Starting at$5/monthSimple, scalable object storageS3-compatible object storageHighly scalableBuilt in CDNView Spaces Object Storage pricing
[H3] Network File Storage
Starting at$0.15/per GiB/monthShared file storageStandard tier: $0.15 per GiB-monthHigh performance tier: $0.30 per GiB-monthStarting from 50 GiBFlat pricing across all supported regionsView Network File Storage pricing
[H3] Volumes
Starting at$10/monthBusiness-ready block storageBlock storageHighly availableEasily scale block storage, resize when needed, and move them between dropletsView Volumes Block Storage pricing
[H2] Networking
[H3] Container Registry
Starting at$0/monthEasily store and manage private container imagesEasily store and manage private container imagesTransfer container images over high-speed HTTPs connections to servers across four continentsView Container Registry pricing
[H3] Load Balancers
Starting at$12/monthLoad balancing, simplifiedImprove availability, performance, and scalabilityLet’s Encrypt and HTTP/3 supportCompatible with Droplets and DigitalOcean KubernetesGlobal Load Balancers now availableView Load Balancer pricing
[H3] Support Plans
Starting at$0/monthUnlimited customized supportFind answers to common questions, development guidelines written by experts and get free email supportIdeal for those testing ideas and hosting small applicationsView Support Plan pricing
[H3] Virtual Private Cloud
Starting at$0/monthSimple, cost effective VPC hostingCreate unlimited VPCs at no additional cost.Ingress data transfer to VPCs is free. Egress data transfer from VPCs to the internet counts against bandwidth quotas.Intra-datacenter VPC peering is free. Inter-datacenter VPC peering is $0.01/GiB.VPC NAT Gateway: $40.00 per node, includes 100 GiB bandwidth (overage $0.01/GiB), supports up to 500,000 connections.View Virtual Private Cloud pricing
[H3] Uptime
Starting at$0/monthAutomated endpoint alertsUptime and latency checksAlerts by email and SlackOne Uptime Check/month included with every accountView Uptime Monitoring pricing
[H2] Security
[H3] Cloud Security Posture Management (CSPM)
Starting at$0/monthStay secure without adding complexityAgentless by designPrioritized findingsGuided remediationUnified visibilityView Cloud Security Posture Management (CSPM) pricingYou've got unique business needs and we've got powerful solutions to meet those needs. Chat with us to get started!Contact sales
[H2] See how much you'll pay with our pricing calculator
We'll do the math
[H3] Platform benefits
All the capabilities you need to build and scale your apps, included at no additional cost.Build and deploy 3 static sites for freeData transfer within and across VPCs in a data center is free. Ingress data transfer is free. Create as many VPCs as you want for no additional costPublic Internet Egress Overage Data transfer is $0.01 per GiBPrivate VPC Egress Overage Data Transfer between data centers is $0.01 per GiBFree Reserved IPs when assigned to a DropletIndustry leading bandwidth pricing, Droplets include free outbound data transfer, starting at 500 GiB / moFree DNS managementFree container registry with 1 repository and 500 MiB storageFree cloud firewallsCollect metrics on visibility, monitor Droplet performance, and get free alerts when problems arise in your infrastructureUse 90,000 GiB-seconds per month for free with DigitalOcean Functions. There are no additional charges for function invocations
[IMG: Bandwidth graphic]
[H3] Experience a 186% return on investment
A Total Economic Impact study by Forrester found that an organization experiences benefits of $2.37 million over three years versus costs of $829,000, adding up to a net present value (NPV) of $1.55 million and an ROI of 186%. An organization using DigitalOcean finds a payback of their investment in less than 6 months.Read the study
[IMG: Laptop graphic]
[H3] Industry-leading bandwidth pricing
Keep your bandwidth costs low with generous transfer quotas and outbound overage at just $0.01/GiB.Go to bandwidth calculator
[H2] Frequently asked questions
What forms of payment do you accept?We accept Visa, Mastercard, American Express, Discover, PayPal, Google Pay, and Apple Pay. Apple pay requires a Safari browser. For additional payment options, including wire transfer, purchase orders, and ACH, please contact us. Note that when you add a card, we may send a temporary pre-authorization request to the issuing bank. This pre-authorization charge is immediately released by DigitalOcean but may take a few days to clear from your card depending on the bank.When will my card be charged?DigitalOcean billing cycles are monthly. Typically, on the first day of each month we invoice and automatically charge your account's primary payment method for the previous month's usage. In some cases, we might charge if your usage exceeds a threshold. You can also login and self pay the balance at any time.Am I charged when I enter my credit card?No. Your card is only charged at the end of the billing cycle or upon exceeding a usage threshold. Pre-authorization charge: When you add a card, we may send a preauthorization request to the issuing bank. This is to verify that the card being added has been issued by the bank and that they will authorize any charges in future. These temporary pre-authorizations are typically $1 but can vary in range and are immediately canceled by us. Depending on your bank, it might take a few days for the charge to clear from the card.Will taxes be included in my monthly invoice?We're required by law to apply taxes in some countries. Click here to learn whether we collect taxes in your country, what the tax rate is, etc.How do I destroy my resources?Check out the docs to learn how to destroy Droplets, Kubernetes clusters, Managed Databases clusters (PostgreSQL, MySQL, Caching), Spaces, Volumes , Firewalls , and Load Balancers.Can I be notified if my bill exceeds a threshold?Yes, you can set up billing alerts and we will email you if the monthly spending exceeds an amount you specify.How does the $5 free credit work?Your card will be charged only after you have utilized the free credits or after the credit expiration period. For example, if you received a $5 credit for 90 days, then that $5 credit is automatically applied to your account. If you spend $3 in that timeframe, your card will not be charged. If you spend $10, the $5 credit will be fully utilized, and your card will be charged only $5. Since the credit is valid for 90 days, you won't be able to use any remaining credit after the 90-day period expires.What's the price for the Marketplace 1-Click Apps?We charge you for the underlying compute on which the 1-Click Apps runs.How do I remove my card from the account?To remove a saved payment method, visit the products billing page and click the … menu of the payment method, then click Delete. In the Confirm Delete Card window that opens, click Delete to remove the card. You cannot remove the default payment method on the account.Can I prepay for my resources?If you are interested in prepayment for resources, contact our experts.Can I have a refund?We do not offer refunds. If there are extenuating circumstances, contact support.
[H2] Still have questions?
Have a complex setup or additional questions around pricing? Contact our sales team to get more information on DigitalOcean pricing.Contact sales
[H2] Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.Sign up