Cloud und Hosting: Release Notes

Refer to Limits & pricing for rates and included usage.

Hybrid search is on by default

New AI Search instances use hybrid search by default. Hybrid search combines semantic vector retrieval with full-text matching. You can choose a different index method when you create an instance.

Refer to Hybrid search for details.

Workers AI embeddings and reranking are included

Workers AI embedding and reranking calls made by AI Search are included in AI Search pricing. These calls no longer appear on your Workers AI bill or in your AI Gateway logs. Generation, query rewriting, and external providers continue to use your account and gateway.

Refer to Limits & pricing for details.

Multimodal model and image support

AI Search supports the @cf/qwen/qwen3-vl-embedding-2b and google-ai-studio/gemini-embedding-2 multimodal embedding models. Search and chat requests can include images through the REST API and public endpoint.

Refer to Supported models for the full list of embedding models.

OCR availability and increased file limits …

A new GA release for the macOS Cloudflare One Client is now available on the stable releases downloads page.

This release includes the following highlights:

• Traffic to split tunnel excluded resources is no longer briefly blocked while the client is connecting or reconnecting. The client now keeps its learned split tunnel configuration across reconnects.
• Support for routing non-RFC 1918 local IPv4 networks through the tunnel when unrestricted LAN inclusion is enabled by policy or MDM.
• Faster connects and lower memory use. The hosts file is now read once and shared across the client’s DNS resolvers instead of being reloaded by each one.

Additional changes and improvements

• Improved reauthentication reliability and fixed an issue where a reauthentication could force a new registration.
• Improved client reaction to the current network lowering its MTU.
• Improved DNS reliability on networks with lower MTUs by clamping the TCP maximum segment size (MSS) for DNS-over-HTTPS connections sent through the tunnel.
• Individual DNS-over-HTTPS queries now time out instead of hanging when the upstream server stops responding.
• Improved API reliability by retrying requests dropped when reusing pooled connections.
• Added an MDM setting to prefer IPv4 when resolving hostnames in proxy mode. The setting is off by default. …

A new GA release for the Windows Cloudflare One Client is now available on the stable releases downloads page.

This release includes the following highlights:

• Traffic to split tunnel excluded resources is no longer briefly blocked while the client is connecting or reconnecting. The client now keeps its learned split tunnel configuration across tunnel reconnections.
• Support for routing non-RFC 1918 local IPv4 networks through the tunnel when unrestricted LAN inclusion is enabled by policy or MDM.
• Improved connection reliability on devices with very large hosts files. The client now detects a large hosts file, allows more time for its initial DNS check, and shows a banner letting the user know that connecting may take longer.
• Faster tunnel reconnections and lower memory use. The hosts file is now read once and shared across the client’s DNS resolvers instead of being reloaded by each one.
• A service recovery mechanism, backed by a Windows scheduled task, now starts the client service on system unlock if it is not already running. This is enabled by default.

Additional changes and improvements

• Improved reauthentication reliability and fixed an issue where a reauthentication could force a new registration.
• Improved client reaction to the current network lowering its MTU. …

A new GA release for the Linux Cloudflare One Client is now available on the stable releases downloads page.

This release includes the following highlights:

• Traffic to split tunnel excluded resources is no longer briefly blocked while the client is connecting or reconnecting. The client now keeps its learned split tunnel configuration across reconnects.
• Support for routing non-RFC 1918 local IPv4 networks through the tunnel when unrestricted LAN inclusion is enabled by policy or MDM.
• Faster tunnel reconnections and lower memory use. The hosts file is now read once and shared across the client’s DNS resolvers instead of being reloaded by each one.
• Added an MDM setting to prefer IPv4 when resolving hostnames in proxy mode. The setting is off by default.

Additional changes and improvements

• Improved reauthentication reliability and fixed an issue where a reauthentication could force a new registration.
• Improved client reaction to the current network lowering its MTU.
• Improved DNS reliability on networks with lower MTUs by clamping the TCP maximum segment size (MSS) for DNS-over-HTTPS connections sent through the tunnel.
• Individual DNS-over-HTTPS queries now time out instead of hanging when the upstream server stops responding.
• Improved API reliability by retrying requests dropped when reusing pooled connections. …

Cloudflare Organizations is now generally available for Enterprise customers and MSSP/Distributor partners.

Organizations provides a top-level container for centrally managing accounts, members, analytics, and shared policies. Organization Super Administrators receive implicit access to every account in their Organization without requiring separate account memberships.

Enterprise customers can manage accounts in a single-tier Organization. MSSP/Distributor partners can use nested sub-organizations to manage customer accounts.

Organization Roles remains in beta, and current product limitations still apply.

For more information, refer to Cloudflare Organizations and current limitations.

SDK Releases

• The Firebase Apple SDK (v13.0.0) is now available. For more details, see the Firebase Apple SDK release notes. To install this SDK, see Add Firebase to your app.

• The Firebase Android SDKs for A/B Testing, AI Logic, Analytics, App Check, App Distribution, Authentication, Cloud Firestore, Cloud Functions, Cloud Messaging, Cloud Storage, Crashlytics, Crashlytics NDK, Dynamic feature modules support, In-App Messaging, Installations, Performance Monitoring, Firebase PNV, Realtime Database, Remote Config, and SQL Connect have been updated. For more details, check out the latest Android Release Notes. To get started with Firebase in Android, see Add Firebase to your Android Project.

• The Firebase Android BoM (Bill of Materials) has been updated to v35.0.0. Learn how to add SDKs to your app using the Firebase BoM.

• The Firebase JavaScript SDK (v13.0.0) is now available. For more details, see the Firebase JavaScript SDK release notes. To install the SDK, see Add Firebase to your JavaScript Project.

On private projects and sites protected with Netlify team login, your Netlify Functions and Edge Functions can now see who is making the request. The signed-in Netlify user is available as context.user, with their user ID, email address, and when their access expires. This function returns the signed-in user's ID, email address, and access expiry as JSON at /whoami, and responds with a 401 when context.user isn't set: // netlify/functions/whoami.ts import type { Config, Context } from '@netlify/functions' export default async (req: Request, context: Context) => { if (!context.user) { return new Response('Unauthorized', { status: 401 }) } return Response.json({ id: context.user.id, email: context.user.email, expiresAt: context.user.expiresAt.toISOString(), }) } export const config: Config = { path: '/whoami' } Previously, protecting a site meant Netlify checked who could visit, but your code couldn't tell who they were. Knowing who's on the other end meant adding a second login of your own on top. Now Netlify verifies the visitor at the edge and passes their identity to your code. Because context.user comes from Netlify and not from the request, a visitor can't impersonate someone else by sending their own headers. With context.user, you can build on the login your team already uses. Examples like:

• Internal dashboards and admin tools that show each person their own data
• Audit logs that record who made a change or triggered an action …

You can now subscribe to Netlify events from ChatGPT and set up automations that respond to what’s happening on your sites. Instead of checking the Netlify dashboard or waiting on an email, you can have ChatGPT act as soon as something happens. Events you can subscribe to include:

• A deploy succeeded
• A build failed
• A form submission came in

For more events to subscribe to, check out our deploy events. Combine events with Netlify plugin and MCP server Events get more useful when you pair them with everything else you can already do through the Netlify ChatGPT plugin and Netlify MCP server. For example, you could set up an automation that:

• Reviews new form submissions and flags the ones that need a follow-up
• Summarizes what changed when a production deploy succeeds

Because these automations live in ChatGPT, you can describe what you want in plain language and adjust it as your workflow changes. Get started Connect Netlify in ChatGPT, then ask it to subscribe to the events you care about for your project. Learn more in our guide to using Netlify with ChatGPT.

Anthropic’s Claude Haiku 5.5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using Claude Haiku 5.5 with the Messages API: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-haiku-5-5', max_tokens: 1024, messages: [ { role: 'user', content: 'Give a concise explanation of how AI works.' } ], }); return Response.json(response); }; Claude Haiku 5.5 is also available across Scheduled Functions, Background Functions, and Edge Functions. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

OpenAI’s Decisions API is now available through Netlify’s AI Gateway with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions to classify, route, and score inputs without managing API keys. Instead of generating prose, the Decisions API answers questions you define about an input, and choice answers are always one of the options you declared. That means there’s no output to parse and nothing unexpected to handle before you branch on the result. The Decisions API is in beta and currently runs on gpt-6-luna. Here’s a Function for an online store that sorts incoming return requests by reason: import type { Config } from "@netlify/functions"; import OpenAI from "openai"; export default async (req: Request) => { const openai = new OpenAI(); const { answers } = await openai.decisions.create({ model: "gpt-6-luna", input: await req.text(), questions: [ { type: "choice", name: "reason", instructions: "Why is the customer returning this item?", choices: [ { value: "wrong_size" }, { value: "defective" }, { value: "not_as_described" }, { value: "changed_mind" }, ], }, ], }); return Response.json(answers[0]); }; export const config: Config = { path: "/api/returns", method: "POST" }; Send it “The jacket fits well, but the zipper came off the second time I wore it” and you get back: { "type": "choice", "name": "reason", "choice": "defective", "probabilities": [ { "value": "wrong_size", "probability": 0.01 }, { "value": "defective", "probability": 0…

Patch Changes

• 5430af1: fix(ai): preserve V2 provider-reported total tokens in raw usage
• f8d8324: fix(ai): publish the latest error after repeated failed stream resume attempts
• 5df41a7: fix(ai): prevent unavailable tools, including tools named after Object.prototype properties, from exposing persisted output to models
• 6a12ead: fix(ai): avoid duplicate slashes in chat reconnect URLs
• Updated dependencies [bedd5bb]
• Updated dependencies [6dd6693]
• Updated dependencies [5607cb2]
• Updated dependencies [fca8a28]
  • @ai-sdk/gateway@3.0.211