---
title: Recent Release Notes
description: DigitalOcean product release notes from the last 90 days.
product: Release Notes
url: https://docs.digitalocean.com/release-notes/recent/
last_updated: "2026-07-30"
---

> **For AI agents:** The documentation index is at [https://docs.digitalocean.com/llms.txt](https://docs.digitalocean.com/llms.txt). Markdown versions of pages use the same URL with `index.html.md` in place of the HTML page (for example, append `index.html.md` to the directory path instead of opening the HTML document).

# Recent Release Notes

Release notes from the last 90 days. Prefer this page (or its [JSON](index.json) twin) with AI tools over `/release-notes/`: some web fetch tools cache popular URLs and can return months-old snapshots without a staleness warning.

For the full historical listing, see the [release notes archive](https://docs.digitalocean.com/release-notes/archive/index.html.md). You can also subscribe to the [release notes RSS feed](https://docs.digitalocean.com/release-notes/index.xml).

## Upcoming Changes

- Managed MySQL 8.0 database clusters are scheduled for forced upgrades to MySQL 8.4 beginning 30 October 2026 during [each cluster’s maintenance window](https://docs.digitalocean.com/products/databases/mysql/how-to/schedule-updates/index.html.md).

  Learn more on [**MySQL 8.0 End of Life and Forced Upgrades Beginning 30 October 2026**](https://docs.digitalocean.com/release-notes/upcoming/mysql-8-eol/index.html.md).

## July 2026

### 27 July

- The following Moonshot AI model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Kimi K3](https://www.kimi.com/blog/kimi-k3)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 24 July

- The following Anthropic model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Claude Opus 5](https://www.anthropic.com/news/claude-opus-5)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 23 July

- The following OpenAI model is deprecated from DigitalOcean Inference as of 23 July 2026:

  - [GPT-5.1-Codex-Max](https://platform.openai.com/docs/models/gpt-5.1-codex-max)

  Migrate to [GPT-5.3-Codex](https://developers.openai.com/api/docs/models/gpt-5.3-codex) (`openai-gpt-5.3-codex`) to avoid service disruption. For information on our model deprecation policy and recommended replacement models, see [Model Support Policy](https://docs.digitalocean.com/products/inference/details/model-support-policy/index.html.md).
- The server-side [model synthesis tool](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/index.html.md#use-fusion-tool) is available in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview) on DigitalOcean Inference. The model synthesis tool is an API-only multi-model tool that runs up to eight analysis models in parallel on the same task, compares their results, and returns one synthesized answer. You can use the model synthesis tool with serverless inference, dedicated inference, and inference routers on the Chat Completions, Responses, and Messages APIs. Opt in from the [**Feature Preview** page](https://cloud.digitalocean.com/account/feature-preview). For more information, see [Use Server-Side Tools](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/index.html.md#use-fusion-tool).
- We now support [prompt caching](https://docs.digitalocean.com/products/inference/details/features/index.html.md#prompt-caching) for [Gemma 4](https://deepmind.google/models/gemma/gemma-4/) for serverless inference.
- Released [v1.164.0 of doctl](https://github.com/digitalocean/doctl/releases/tag/v1.164.0), the official DigitalOcean CLI. This release adds commands for managing Secrets Manager secrets and [Network File Storage](https://docs.digitalocean.com/products/nfs/index.html.md) access points.
- We have updated the following buildpack for App Platform:

  - [Node.js buildpack](https://docs.digitalocean.com/products/app-platform/reference/buildpacks/nodejs/index.html.md): We added the following Node.js versions and updated the buildpack to version `342`. Visit [the Node.js buildpack](https://docs.digitalocean.com/products/app-platform/reference/buildpacks/nodejs/index.html.md#specify-a-nodejs-engine) to learn more about specifying a Node.js engine version.

    - Node.js 24.15.0

### 15 July

- The [Gradient AI Go Library](https://gradientai-sdk.digitalocean.com/api/go) is deprecated. Use the official [DigitalOcean Go SDK (Godo)](https://github.com/digitalocean/godo) or the [DigitalOcean API](https://docs.digitalocean.com/reference/api/index.html.md) directly. For installation and quickstart examples, see [SDK and Client Libraries](https://docs.digitalocean.com/reference/libraries/index.html.md).
- The [Gradient AI Python SDK](https://gradientai-sdk.digitalocean.com/api/python) is deprecated. Use the official [DigitalOcean Python SDK (PyDo)](https://github.com/digitalocean/pydo) or the [DigitalOcean API](https://docs.digitalocean.com/reference/api/index.html.md) directly. For installation and quickstart examples, see [SDK and Client Libraries](https://docs.digitalocean.com/reference/libraries/index.html.md).
- The [Gradient AI TypeScript SDK](https://github.com/digitalocean/gradient-typescript) is deprecated. Use the official [DigitalOcean TypeScript SDK (DoTs)](https://github.com/digitalocean/dots) or the [DigitalOcean API](https://docs.digitalocean.com/reference/api/index.html.md) directly. For installation and quickstart examples, see [SDK and Client Libraries](https://docs.digitalocean.com/reference/libraries/index.html.md).

### 10 July

- The following OpenAI models are now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md):

  - [GPT-5.6 Sol](https://developers.openai.com/api/docs/models/gpt-5.6-sol)
  - [GPT-5.6 Terra](https://developers.openai.com/api/docs/models/gpt-5.6-terra)
  - [GPT-5.6 Luna](https://developers.openai.com/api/docs/models/gpt-5.6-luna)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 9 July

- Ubuntu 25.10 has reached end of life. Per our [image deprecation policy](https://docs.digitalocean.com/products/droplets/details/image-deprecation/index.html.md), this image is available exclusively via the API for the next 30 days before we remove it from our platform.

### 8 July

- DigitalOcean Kubernetes (DOKS) now supports [automatic node remediation](https://docs.digitalocean.com/products/kubernetes/how-to/configure-automatic-node-remediation/index.html.md) in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). DOKS can automatically replace worker nodes that stay unhealthy, based on Kubernetes node conditions and rules you define.

  The Data Plane Operator runs in your cluster, watches node conditions, and replaces a worker when a condition matches your rules for a configured duration. You can act on standard kubelet conditions, such as `Ready`, and on custom conditions you publish from your own health checks. You configure remediation by deploying the `DataPlaneOperatorConfig` and `NodeRemediationConfig` custom resources to your cluster.

### 2 July

- DigitalOcean Kubernetes (DOKS) now runs a [node readiness controller](https://docs.digitalocean.com/products/kubernetes/how-to/use-node-readiness-controller/index.html.md) in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). The controller watches node conditions and holds `NoSchedule` taints on nodes until required components, including GPU drivers on GPU nodes, report healthy, which prevents pods from scheduling onto nodes that are not yet ready. DOKS deploys and manages the controller automatically.

  For GPU node pools, you can also customize which GPU health metrics gate scheduling, without redeploying any components.

### 1 July

- DigitalOcean [Managed Weaviate](https://docs.digitalocean.com/products/vector-databases/weaviate/index.html.md) is now in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview) and enabled for all users. Weaviate is a fully managed vector database for retrieval-augmented generation and semantic search workloads.

  Create clusters from the [Vector Databases page](https://cloud.digitalocean.com/vectordatabases), the [`/v2/vector-databases` API](https://docs.digitalocean.com/reference/api/reference/vector-databases/index.html.md), or [`doctl vector-databases`](https://docs.digitalocean.com/reference/doctl/reference/vector-databases/index.html.md). Select **Weaviate** as the engine and review the public preview disclaimer and legal terms in the create flow. For setup, limits, and pricing, see [Managed Weaviate](https://docs.digitalocean.com/products/vector-databases/weaviate/index.html.md).
- [Claude Fable 5](https://www.anthropic.com/claude/fable) is available again on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md). For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).
- [Prompt caching](https://docs.digitalocean.com/products/inference/details/features/index.html.md#prompt-caching) for open-source models in serverless inference chat completions and responses API is now in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). Open-source models cache context automatically, so you do not need to set the `cache_control` or `prompt_cache_retention` parameters.

  Prompt caching is available for the following open-source models:

  - DeepSeek V3.2
  - DeepSeek V4 Pro
  - DeepSeek V4 Flash
  - Kimi K2.5
  - Kimi K2.6
  - GLM 5
  - GLM-5.1
  - GLM-5.2
  - gpt-oss-120b
  - MiMo V2.5
  - MiMo V2.5 Pro
  - MiniMax M2.5
  - Qwen 3.5
  - Qwen3 Coder Flash

  For more information, see [Use Prompt Caching](https://docs.digitalocean.com/products/inference/how-to/use-prompt-caching/index.html.md#open-source-models).
- The [Ubuntu 26.04 LTS](https://canonical.com/blog/canonical-releases-ubuntu-26-04-lts-resolute-raccoon) (`ubuntu-26-04-x64`) base image is now available in the control panel and via the API.
- [Invoice](https://docs.digitalocean.com/platform/billing/invoices/index.html.md) and [Billing Insights](https://docs.digitalocean.com/platform/billing/spend-by-date-range/index.html.md) CSV files now include a `tag_name` column that lists the tags applied to each resource. Tag information is included only for resource usage on or after 1 July 2026.

## June 2026

### 30 June

- DigitalOcean Managed Valkey database clusters now support custom CNAME records, allowing clients to connect through your own hostname instead of the default `*.db.ondigitalocean.com` address. Custom CNAMEs are available through the API when creating clusters or when updating an existing cluster, and apply to the public network connection only. For more information, see [Configure Custom CNAMEs for Valkey](https://docs.digitalocean.com/products/databases/valkey/how-to/configure-custom-cnames/index.html.md).
- [Private Droplets](https://docs.digitalocean.com/products/droplets/details/private-droplets/index.html.md) are now generally available in all regions. Private Droplets have no public network interface and no public IP address, using VPC-only networking with automatic integration with VPC NAT gateway, VPC peering, and VPC private DNS. See the [Private Droplets documentation](https://docs.digitalocean.com/products/droplets/details/private-droplets/index.html.md) for setup instructions and limitations.
- The following agent evaluation metrics are deprecated and should no longer be used:

  - Tone
  - Retrieved Chunk Usage
  - Prompt Perplexity

  Use the currently supported metrics listed in [Agent Evaluation Metrics](https://docs.digitalocean.com/products/inference/reference/agent-evaluation-metrics/index.html.md) instead. To monitor deployed agent behavior outside of evaluations, use [Agent Metrics and Runtime Logs](https://docs.digitalocean.com/products/inference/how-to/view-agent-observability/index.html.md).
- The following Anthropic model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Claude Sonnet 5](https://www.anthropic.com/news/claude-sonnet-5)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).
- Agent evaluations support for the Agent Development Kit (ADK), previously in preview, is now removed.

  To evaluate agents, use [agent evaluations via the DigitalOcean Control Panel](https://docs.digitalocean.com/products/inference/how-to/evaluate-agents/index.html.md) for supported agent types. To monitor ADK agent behavior, use [Agent Metrics and Runtime Logs](https://docs.digitalocean.com/products/inference/how-to/view-agent-observability/index.html.md).
- Insights, agent tracing, and conversation logs are deprecated for all agents, including agents created through the Control Panel, CLI, API, and Agent Development Kit (ADK).

  To monitor deployed agent behavior, use [Agent Metrics and Runtime Logs](https://docs.digitalocean.com/products/inference/how-to/view-agent-observability/index.html.md) instead.
- The Agent Evaluations MCP server tool has been renamed to [Evaluations](https://docs.digitalocean.com/reference/mcp/evaluations-mcp-tools/index.html.md).
- Custom metrics are now available for [DigitalOcean Evaluations](https://docs.digitalocean.com/products/inference/how-to/evaluate-models/index.html.md). You can define your own metrics to evaluate model behavior against criteria specific to your use case.
- [DigitalOcean Evaluations](https://docs.digitalocean.com/products/inference/how-to/evaluate-models/index.html.md) is now generally available. Use Evaluations to create test cases, run evaluation datasets, and measure model performance against selected metrics.
- Presets are now available for [DigitalOcean Evaluations](https://docs.digitalocean.com/products/inference/how-to/evaluate-models/index.html.md). You can save and reuse evaluation configurations, including the candidate model, system prompt, hyperparameters, judge model, and metrics.
- Model Evaluations is now renamed to [DigitalOcean Evaluations](https://docs.digitalocean.com/products/inference/how-to/evaluate-models/index.html.md).

### 29 June

- Serverless Inference now requires a positive prepaid account balance before you can send inference requests. Usage charges are deducted from this balance, and access is suspended if it reaches $0. You can add a prepayment manually or enable auto-reload to replenish your balance automatically. For more information, see [Manage Serverless Inference Prepayment](https://docs.digitalocean.com/products/inference/how-to/manage-serverless-inference-prepayment/index.html.md).
- The DigitalOcean Control Panel now supports light and dark themes. From the profile menu in the top right corner of the control panel, you can [set your theme](https://docs.digitalocean.com/platform/accounts/theme/index.html.md) to a light or dark appearance, or match your operating system’s appearance setting.

### 25 June

- You can now attach [Network File Storage](https://docs.digitalocean.com/products/nfs/index.html.md) shares to multiple VPC networks, and expose specific subdirectories to single VPC networks by creating access points.

  A share can connect to up to 10 VPC networks in the same region. Access points restrict clients to a specific path within the share, and are isolated from one another so that clients on one cannot see the directories governed by another. This lets you host multiple tenants on a single share, each scoped to their own directory. For details, see [How to Create and Delete Network File Storage Access Points](https://docs.digitalocean.com/products/nfs/how-to/manage-access-points/index.html.md).
- Released [v1.163.0 of doctl](https://github.com/digitalocean/doctl/releases/tag/v1.163.0), the official DigitalOcean CLI. This release adds a [`vector-databases`](https://docs.digitalocean.com/reference/doctl/reference/vector-databases/index.html.md) command group for managing [vector databases](https://docs.digitalocean.com/products/vector-databases/index.html.md).

### 24 June

- [Single sign-on (SSO) with OIDC](https://docs.digitalocean.com/products/kubernetes/how-to/configure-single-sign-on-for-clusters/index.html.md) for DigitalOcean Kubernetes (DOKS) clusters is now in [general availability](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#general-availability). You can authenticate users to your Kubernetes clusters through an identity provider like Auth0, authentik, JumpCloud, Keycloak, or Okta, instead of using token-based authentication.

  SSO is configured per cluster with an issuer URL and client ID from your identity provider. You can enable it using [doctl](https://docs.digitalocean.com/reference/doctl/reference/kubernetes/cluster/index.html.md), the [DigitalOcean API](https://docs.digitalocean.com/reference/api/digitalocean/index.html.md#tag/Kubernetes), or [Terraform](https://docs.digitalocean.com/reference/terraform/reference/resources/kubernetes_cluster/index.html.md).
- The following Z.ai model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [GLM-5.1](https://huggingface.co/zai-org/GLM-5.1)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).
- A [Fedora 44](https://docs.fedoraproject.org/en-US/releases/f44/) (`fedora-44-x64`) Droplet base image is now available in the Control Panel and through the API.

### 22 June

- The following Z.ai model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [GLM-5.2](https://huggingface.co/zai-org/GLM-5.2)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 18 June

- To comply with [Peru’s tax regulation for digital services](https://www.sunat.gob.pe/legislacion/superin/2024/000173-2024.pdf), DigitalOcean charges Value Added Tax (VAT) for customers with a tax location in Peru, beginning on 1 June 2026. These charges appear on invoices issued on and after 1 July 2026. [Learn more about taxes in Peru](https://docs.digitalocean.com/platform/billing/taxes/per/index.html.md).

### 17 June

- The following Xiaomi model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [MiMo-V2.5-Pro](https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).
- DigitalOcean Inference supports server-side tools on serverless inference, dedicated inference, and inference routers. You can add the following tools:

  - Web search, web fetch, knowledge base retrieval, and remote MCP server tools to your requests in the [Chat Completions](https://docs.digitalocean.com/products/inference/how-to/use-chat-completions-api/index.html.md) and [Responses](https://docs.digitalocean.com/products/inference/how-to/use-responses-api/index.html.md) APIs.
  - Provider-native tools such as bash, text editor, computer use, and web fetch for Anthropic models with the [Messages API](https://docs.digitalocean.com/products/inference/how-to/use-messages-api/index.html.md).
  - Function calling and tool search for OpenAI models on the Responses API, and Anthropic models on the Messages API.

  Web search and web fetch are in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). For more information, see [Use Server-Side Tools](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/index.html.md).
- Updated CentOS Stream 9 and CentOS Stream 10 (`centos-stream-9-x64`, `centos-stream-10-x64`) Droplet base images require a minimum Droplet size of `s-1vcpu-1gb`. You cannot create Droplets with these images on the `s-1vcpu-512mb-10gb` plan because the image exceeds the available disk size for that plan. For more information, see [Linux Images for Droplets](https://docs.digitalocean.com/products/droplets/details/images/index.html.md).

### 16 June

- Released [v1.162.0 of doctl](https://github.com/digitalocean/doctl/releases/tag/v1.162.0), the official DigitalOcean CLI. This release adds support for the PostgreSQL and MySQL [Advanced Edition](https://docs.digitalocean.com/products/databases/postgresql/how-to/use-advanced-edition-clusters/index.html.md) engines, `advanced_pg` and `advanced_mysql`, in the `databases` commands.

### 15 June

- The following Anthropic models are deprecated from DigitalOcean Inference as of 15 June 2026:

  - [Claude Opus 4](https://www.anthropic.com/claude/opus)
  - [Claude Sonnet 4](https://www.anthropic.com/claude/sonnet)

  Migrate to [Claude Opus 4.8](https://www.anthropic.com/claude/opus) (`anthropic-claude-opus-4.8`) and [Claude Sonnet 4.6](https://www.anthropic.com/claude/sonnet) (`anthropic-claude-4.6-sonnet`), respectively, to avoid service disruption. For information on our model deprecation policy and recommended replacement models, see [Model Support Policy](https://docs.digitalocean.com/products/inference/details/model-support-policy/index.html.md).

### 12 June

- The following Xiaomi model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [MiMo-V2.5](https://huggingface.co/XiaomiMiMo/MiMo-V2.5)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).
- Claude Fable 5 is no longer available on DigitalOcean Inference. Access to all other Anthropic models remains available. For more information, see [the Anthropic statement on Claude Fable 5](https://www.anthropic.com/news/fable-mythos-access).

### 10 June

- We support passthrough tool search on the [Messages API](https://docs.digitalocean.com/products/inference/how-to/use-messages-api/index.html.md) for Anthropic models and the [Responses API](https://docs.digitalocean.com/products/inference/how-to/use-responses-api/index.html.md) for OpenAI models, enabling deferred loading of tools in agentic workflows. There is no additional cost to using tool search. For more information, see [Use Server-Side Tools](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/index.html.md#tool-search).
- Debian 12 [reached end of life](https://www.debian.org/releases/) on 10 June 2026. Per our [image deprecation policy](https://docs.digitalocean.com/products/droplets/details/image-deprecation/index.html.md), this image is available exclusively via the API for the next 30 days before we remove it from our platform.

### 9 June

- The following Anthropic model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Claude Fable 5](https://www.anthropic.com/news/claude-fable-5-mythos-5)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 4 June

- The following NVIDIA model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Nemotron 3 Ultra](https://developer.nvidia.com/nemotron)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 3 June

- The public endpoint when creating a dedicated inference deployment is now disabled by default. For more information on how to enable access, see [Use Dedicated Inference Endpoint](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md#use-the-dedicated-inference-endpoint).

## May 2026

### 28 May

- You can now use the [DigitalOcean Control Panel](https://cloud.digitalocean.com/vectordatabases) to create, connect to, tag, resize, and restore Managed Weaviate clusters (in [private preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#private-preview)). See the [Managed Weaviate docs](https://docs.digitalocean.com/products/vector-databases/weaviate/index.html.md) for more information.
- The following Anthropic model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Claude Opus 4.8](https://www.anthropic.com/news/claude-opus-4-8)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md#foundation-models).

### 27 May

- The following DeepSeek model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [dedicated inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md), and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [DeepSeek V4 Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md).
- Fedora 42 has reached end of life. Per our [image deprecation policy](https://docs.digitalocean.com/products/droplets/details/image-deprecation/index.html.md), this image is available exclusively via the API for the next 30 days before we remove it from our platform.

### 20 May

- [Request-based autoscaling](https://docs.digitalocean.com/products/app-platform/how-to/scale-app/index.html.md#configure-request-based-autoscaling) for App Platform is now in [general availability](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#general-availability). Service components can scale automatically based on HTTP traffic metrics, including requests per second and P95 request duration, in addition to or instead of CPU utilization. Request-based autoscaling works with both shared and dedicated CPU plans.

  Configure request-based autoscaling in the [DigitalOcean Control Panel](https://cloud.digitalocean.com/apps), with the [API](https://docs.digitalocean.com/reference/api/reference/apps/index.html.md#apps_update), or with [doctl](https://docs.digitalocean.com/reference/doctl/reference/apps/update/index.html.md).

### 19 May

- MySQL 8.4 is [now available for database clusters](https://docs.digitalocean.com/products/databases/mysql/how-to/create/index.html.md). New clusters use MySQL 8.4 by default. For version support and MySQL 8.0 end of life, see [MySQL Limits](https://docs.digitalocean.com/products/databases/mysql/details/limits/index.html.md).
- DigitalOcean Kubernetes (DOKS) now supports [single sign-on (SSO) with OIDC](https://docs.digitalocean.com/products/kubernetes/how-to/configure-single-sign-on-for-clusters/index.html.md) in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). You can authenticate users to your Kubernetes clusters through an identity provider like Auth0, JumpCloud, Keycloak, or Okta, instead of using token-based authentication.

  SSO is configured per cluster with an issuer URL and client ID from your identity provider. You can enable it using [doctl](https://docs.digitalocean.com/reference/doctl/reference/kubernetes/cluster/index.html.md).

### 12 May

- Registered businesses in Tanzania may now be required to withhold 15% of the gross amount of payments for digital services from DigitalOcean under the Tanzania Income Tax Act. [Learn more about taxes in Tanzania](https://docs.digitalocean.com/platform/billing/taxes/tza/index.html.md).

### 5 May

- The following Moonshot AI model is now available on DigitalOcean Inference for [serverless inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md), [Agent Development Kit](https://docs.digitalocean.com/products/inference/how-to/build-agents-using-adk/index.html.md) and [agents](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md):

  - [Kimi K2.6](https://www.kimi.com/ai-models/kimi-k2-6)

  For more information, see the [Available Models page](https://docs.digitalocean.com/products/inference/details/models/index.html.md).
- A [remote MCP server](https://docs.digitalocean.com/reference/mcp/index.html.md) is now available for Functions, providing API-based access for AI tools to manage DigitalOcean resources.