New, Oct 22. Every Oracle Cloud and DigitalOcean service and release note, with their equivalents on the other clouds.
Simple cloud for developers and startups, from Droplets to managed databases and AI inference.
The following Reflection AI model is now available on DigitalOcean Inference for serverless inference: Beam
The following Reflection AI model is now available on DigitalOcean Inference for serverless inference:
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA Nemotron 3.5 Super VL
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference:
In public preview, you can now create spend alerts for Serverless Inference model access keys.
Each key’s spend is tracked against its own monthly budget, and you receive email alerts as it crosses the thresholds you choose.
DigitalOcean Harness Runtime now supports OpenHands agents.
Run the OpenHands Agent Server in an isolated sandbox, create agents from OpenHands Agent Canvas or the DigitalOcean API, and connect a model such as one from DigitalOcean Serverless Inference. To set up an agent, see How to Run an OpenHands Agent on DigitalOcean Harness Runtime.
Inference Router has been redesigned as a single managed router.
Send requests to the inference-router model name, optionally with a routing_preference of balanced, budget, or quality, and the router selects the best model for each request.
Simulation is now available in public preview.
Simulation tests agent behavior through generated, multi-turn conversations using scenario sets, user simulator models, judge models, and conversational metrics.
The following Anthropic model is now available on DigitalOcean Inference for serverless inference: Claude Haiku 5.5
The following Anthropic model is now available on DigitalOcean Inference for serverless inference:
DigitalOcean MicroVMs are available in public preview in MKC1.
MicroVMs are lightweight virtual machines that run a container image in its own kernel, pause automatically when idle, and resume on the next request with memory, files, and processes intact.
Prompt caching for DigitalOcean-hosted models is now in general availability.
All DigitalOcean-hosted models cache context automatically, with no code changes and no cache-write charge. Cache affinity routes requests with matching prefixes to the replica that holds the cache.
When you upgrade an existing DigitalOcean Kubernetes (DOKS) cluster to version 1.37 or later, DOKS automatically enables the CoreDNS Cluster Proportional…
When you upgrade an existing DigitalOcean Kubernetes (DOKS) cluster to version 1.37 or later, DOKS automatically enables the CoreDNS Cluster Proportional Autoscaler (CPA) plugin if CoreDNS is still running the default of two replicas.
Starting with DOKS 1.37, GPU device plugins are no longer enabled by default on clusters with GPU nodes.
Dynamic Resource Allocation (DRA) drivers are available as opt-in cluster plugins ( nvidia_gpu_dra_driver or amd_gpu_dra_driver ). Device plugins ( nvidia_gpu_device_plugin or amd_gpu_device_plugin ) remain available but must be enabled explicitly.
DigitalOcean Signals is now available in public preview for Harness Runtime agents and Serverless Inference.
Signals detects behavioral signals in conversations, such as a user asking for a human, a failed tool call, or an execution loop, so you can find the conversations that went wrong without reading every transcript. Signals collects data only after you opt in.
Managed databases are available in Memphis ( mem1 ) on AMDv5 plans only.
Storage-Optimized plans are now available for Kafka and OpenSearch clusters in mem1 only. See the regional availability matrix for current coverage by engine.
The Cost Analysis tab of the Billing page now includes Serverless Inference Live Usage, which lists the estimated cost and token counts of your Serverless…
The Cost Analysis tab of the Billing page now includes Serverless Inference Live Usage, which lists the estimated cost and token counts of your Serverless Inference requests by model and model access key, for both teams and organizations.
46 services
1-Click Models
1-Click Models let you deploy third-party generative AI models on GPU Droplets with no additional setup or configuration.
Bare Metal GPUs
Bare Metal GPUs are dedicated, single-tenant servers with eight GPUs per machine.
Evaluations
DigitalOcean Evaluations measure model, Inference Router, and agent performance using dataset evaluations and simulations.
GPU Droplets
GPU Droplets are VMs with GPUs in a single or 8 GPU configuration.
Inference
Inference is a centralized interface for browsing foundation models, comparing capabilities and pricing, testing models in the Model Playground, and …
Managed Agents
DigitalOcean's cloud platform for running and scaling AI agents, and governing the actions they take.
Paperspace
Paperspace is a cloud-based machine learning platform that offers GPU-powered virtual machines and a Kubernetes-based container service.
App Platform
App Platform is a fully managed Platform-as-a-Service (PaaS) that deploys applications from Git repositories or container images.
Cloudways
Cloudways is a managed cloud hosting platform where teams can build, deploy, and scale web applications.
Droplets
DigitalOcean Droplets are Linux-based virtual machines (VMs).
Functions
DigitalOcean Functions is a function as a service (FaaS) offering that lets you run your local serverless code in the cloud using Node.js, Python, Go, …
Kubernetes
DigitalOcean Kubernetes (DOKS) is a managed Kubernetes service that lets you deploy Kubernetes clusters without the complexities of handling the …
MicroVMs
Lightweight virtual machines that run a container image in its own kernel, pause when idle, and resume on the next request with memory and processes …
Backups
Enable backups to automatically create system-level disk images weekly or daily with no configuration required.
Container Registry
Store Docker images in your own private registry.
Custom Images
Upload custom images to use guest operating systems and pre-packaged libraries on DigitalOcean Droplets.
Marketplace
Create new Droplets or Kubernetes clusters with 1-Click Apps preconfigured for WordPress, LAMP, Ghost, and hundreds more.
SnapShooter
SnapShooter is a cloud backup and recovery solution.
Snapshots
Create snapshots to save on-demand copies of DigitalOcean Droplets or volumes to your account.
Agent Data Services
DigitalOcean Agent Data Services is a fully managed service that turns raw multimodal and behavioral data into AI-ready data that you can query as …
Knowledge Bases
Store, index, and retrieve data from files, websites, and Spaces buckets to power retrieval-augmented generation.
Managed Databases
Run fully managed database clusters running your choice of database engine and avoid manual setup and maintenance.
Managed Kafka
Kafka is an open-source distributed event and stream-processing platform built to process demanding real-time data feeds.
Managed MongoDB
MongoDB is a source-available cross-platform document-oriented database program for high-volume storage.
Managed MySQL
MySQL is an open source, object-relational database built with speed and reliability in mind.
Managed OpenSearch
OpenSearch is an open-source search and analytics suite which allows you to forward logs.
Managed PostgreSQL
PostgreSQL is an open source, object-relational database built with extensibility, data integrity, and speed in mind.
Managed Valkey
Valkey is a high-performance, open-source database that stores key-value data in memory, and is designed for caching, message queues, and primary …
Vector Databases
DigitalOcean Vector Databases let you store and search vector embeddings for retrieval-augmented generation, semantic search, and other AI workloads, …
CSPM
Identify, prioritize, and remediate security risks across your DigitalOcean resources.
DigitalOcean API
Manage DigitalOcean resources programmatically over HTTP
doctl
The official DigitalOcean command-line interface
Insights
Explore metrics, logs, traces, dashboards, and metric alerts for supported resources.
Monitoring
DigitalOcean Monitoring is a free, opt-in service that helps you track Droplet resource usage, view performance metrics, and receive alerts.
Projects
Create projects to organize your DigitalOcean resources into groups that fit the way you work.
Uptime
Check the health of URLs, hostnames, and IP addresses, and set alerts for latency, downtime, and expired SSL certificates
Cloud Firewalls
Restrict traffic with network-based, stateful firewalls for Droplets.
DDoS Protection
DigitalOcean DDoS Protection provides free, always-on protection from distributed denial-of-service (DDoS) attacks for applicable DigitalOcean …
Domains and DNS
Manage DNS for Droplets, DigitalOcean Load Balancers, and non-DigitalOcean resources all in the same place.
IPv6
Compared to IPv4, IPv6 provides a larger address space, increased security, and other benefits.
Load Balancers
Load balancers distribute traffic across pools of backend resources for high availability setups.
Reserved IPs
DigitalOcean Reserved IPs are publicly-accessible static IP address that you can assign to Droplets and instantly remap to other Droplets in the same …
VPC
A Virtual Private Cloud (VPC) is a private network interface for collections of DigitalOcean resources.
Network File Storage
Network File Storage is a fully managed, POSIX-compliant file storage solution built for demanding workloads.
Spaces Object Storage
Spaces Object Storage is an S3-compatible service for storing and serving large amounts of data.
Volumes Block Storage
Volumes are network-based block devices that provide additional data storage for Droplets.
