D
14 September 2026 (inference)
The following DeepSeek model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: DeepSeek V4.1 Flash For more information, see the Available Models page.
D
10 September 2026 (load-balancers, kubernetes)
The DigitalOcean Control Panel now supports adding and removing allow and deny rules based on IP addresses and CIDR ranges when you create or manage regional load balancers that use HTTP or Network traffic management. See How to Create …
D
9 September 2026 (kubernetes)
DigitalOcean Kubernetes (DOKS) now supports Spot GPU node pools in public preview. You can run worker nodes on interruptible Spot GPU capacity for AMD Instinct MI350X and MI355X and NVIDIA B300 GPUs, at a lower, variable rate than on-demand …
D
8 September 2026 (inference)
The following models are deprecated from DigitalOcean Inference as of 8 September 2026: Kimi K2.5 GLM 5 GLM-5.1 Nemotron-3-Super-120B (Public Preview) Migrate Kimi K2.5 to Kimi K3 (kimi-k3), GLM 5 and GLM-5.1 to GLM-5.3 (glm-5.3), and …
D
4 September 2026 (inference)
The following OpenAI model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: GPT-6 Astra For more information, see the Available Models page.
D
1 September 2026 (inference)
The following Anthropic model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: Claude Fable 5.1 For more information, see the Available Models page.
D
1 September 2026 (kubernetes)
DigitalOcean Kubernetes (DOKS) now supports Isolated Worker Nodes in public preview. Every worker node in an isolated cluster runs without a public IPv4 address, so nodes are removed from the public internet at the network level rather than …
D
1 September 2026 (kubernetes)
The peer-to-peer OCI registry plugin for DigitalOcean Kubernetes (DOKS) is now in general availability. The plugin uses Spegel to mirror container image layers across cluster nodes, so a node can pull layers from a peer that already has …
D
28 August 2026 (inference)
The following Z.ai model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: GLM-5.3 For more information, see the Available Models page.
D
27 August 2026 (inference)
The following Z.ai model is now available on DigitalOcean Inference for serverless inference, dedicated inference, Agent Development Kit, and agents: GLM-5.3 Flash For more information, see the Available Models page.
D
25 August 2026 (droplets, kubernetes)
v5 Droplet configurations are now available in the atl1, ric1, mkc1, and mem1 datacenters. They run on 5th Generation AMD EPYC processors for higher per-core performance and let you size compute, memory, storage, and networking …
D
24 August 2026 (droplets)
Updated NVIDIA AI/ML Ready (gpu-h100x1-base, gpu-h100x8-base) Droplet base images are now available in the Control Panel and through the API. The images are based on Ubuntu 24.04 (upgraded from Ubuntu 22.04) and include NVIDIA driver …
D
20 August 2026 (inference)
Qwen3.8-2.4T-A95B model available on DigitalOcean Inference has been upgraded to Qwen3.8-Max. Qwen3.8-Max supports vision and video input and a 1M-token context window. For more information, see the Available Models page.
D
19 August 2026 (inference)
Inference Router now uses cache-aware routing to maximize prompt cache reuse and automatically applies prompt caching to eligible Anthropic requests. You can opt out of prompt caching for supported models with X-Model-Affinity: none and …
D
18 August 2026 (inference)
The following open-source models are deprecated from DigitalOcean Inference as of 18 August 2026: Llama 3.3 Instruct-70B DeepSeek R1 Distill Llama 70B Qwen3-32B Qwen3 Coder Flash Migrate Llama 3.3 Instruct-70B to Llama 4 Maverick 17B 128E …
D
14 August 2026 (inference)
The following DeepSeek model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: DeepSeek V4 Pro 0813 For more information, see the Available Models page.
D
13 August 2026 (kubernetes)
DigitalOcean Kubernetes (DOKS) now supports Dynamic Resource Allocation (DRA) drivers for NVIDIA and AMD GPU node pools in public preview, starting with DOKS 1.36.3-do.0. DRA is an opt-in alternative to the managed GPU device plugins. …
D
12 August 2026 (inference)
The following Alibaba model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: Qwen3.8-2.4T-A95B For more information, see the Available Models page.
D
12 August 2026 (cspm)
Cloud Security Posture Management (CSPM) paid plans support Managed Rules, which let you enable or disable CSPM rules for your entire team. To exclude specific resources while keeping a rule enabled for the rest of the team, suppress …
D
12 August 2026 (inference)
The following Alibaba model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: Qwen3.8-2.4T-A95B (Public Preview) For more information, see the Available Models page.
D
10 August 2026 (platform)
We have launched the Memphis, Tennessee, USA (mem1) datacenter, which supports AMD Instinct MI355X Spot GPU Droplets and many other products. For the full list of supported products, see the regional availability matrix.
D
10 August 2026 (droplets)
AMD Instinct MI355X GPUs are now available in MEM1 as Spot GPU Droplets in 1- and 8-GPU configurations. Spot prices vary daily based on available capacity. For pricing, see Spot GPU Droplet pricing.
D
10 August 2026 (droplets)
Spot GPU Droplets are now available in public preview for supported GPUs in single-GPU and 8-GPU configurations. Pricing may change daily based on capacity. To compare the capacity tiers, see Spot GPU Droplets vs On-Demand GPU Droplets.
D
10 August 2026 (container-registry)
DigitalOcean Container Registry (DOCR) now provides mirror registries: DigitalOcean-curated regional mirrors of popular AI container images, available in 11 datacenter regions. You can pull nvidia/pytorch and rocm/pytorch images from a …
D
6 August 2026 (inference)
The following DeepSeek model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: DeepSeek V4 Flash 0731 For more information, see the Available Models page.
D
6 August 2026 (droplets)
DigitalOcean has patched “Safe RET” across our AMD Droplet fleet. We applied the fix at the infrastructure level, and no customer action is required. For more information, see AMD’s security bulletin, AMD-SB-7061.
D
5 August 2026 (billing, organizations)
Spend alerts are now generally available for teams and organizations, replacing billing alerts. You can create multiple alerts with incremental percentage thresholds, scoped to total spend, specific products, or, for organizations, specific …
D
5 August 2026 (inference)
The following Anthropic model is deprecated from DigitalOcean Inference as of 5 August 2026: Claude Opus 4.1 Migrate to Claude Opus 4.8 (anthropic-claude-opus-4.8) to avoid service disruption. For information on our model deprecation policy …
D
4 August 2026 (platform)
We have launched the Kansas City, Missouri, USA (mkc1) datacenter, which supports GPU Droplets, Kubernetes, Managed Databases, Spaces object storage, App Platform, Functions, and many other products. For the full list of supported products, …
D
4 August 2026 (firewalls, networking)
Cloud firewall rules now support an action of allow or deny. Deny rules let you block traffic from specific sources, such as known malicious IP addresses, while allowing broader access to your services. Deny rules take precedence over allow …