Changelog

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.
• Fixed the client reconnecting while Emergency Disconnect was active after switching organizations or re-registering.
• Fixed the client being unable to connect after an upgrade when its stored registration credentials no longer matched its configuration.
• Fixed the client service restarting unexpectedly when it was slow to respond, such as after waking from sleep.
• Fixed Extra Logging failing to capture packets across all interfaces.
• Fixed an issue that could prevent remote diagnostics from completing.
• Fixed DNS connectivity checks failing on IPv6-only networks.
• Fixed the client service exiting when its route-monitoring socket was closed after sleep or wake.
• Fixed DNS enforcement checks making the client service unresponsive on systems with large routing tables.
• Fixed slow captive portal checks causing the client service to become unresponsive or restart while connecting.
• Fixed a race when switching tunnel protocols during key rotation that could prevent WireGuard from connecting.
• Fixed the client continuing to report “No network” after a successful manual disconnect.
• Fixed a client UI crash that could occur when the daemon connection was reset during an IPC request.
• Fixed a startup crash when date formatting data for the system locale had not yet loaded.

Known issues

• None

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.
• 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.
• The client no longer requires the Windows WLAN AutoConfig service to be running.
• Fixed the client reconnecting while Emergency Disconnect was active after switching organizations or re-registering.
• Fixed the client being unable to connect after an upgrade when its stored registration credentials no longer matched its configuration.
• Fixed the client service restarting unexpectedly when it was slow to respond, such as after waking from sleep.
• Fixed the client service failing to restart after an unexpected termination.
• Fixed the client UI getting stuck in a connecting state after sleep and wake even though the tunnel was connected.
• Fixed slow captive portal checks causing the client service to become unresponsive or restart while connecting.
• Fixed a race when switching tunnel protocols during key rotation that could prevent WireGuard from connecting.
• Fixed the client continuing to report “No network” after a successful manual disconnect.
• Fixed Digital Experience Monitoring (DEX) HTTP tests failing TLS validation.
• Fixed latency spikes and traffic interruptions during TPM-backed API authentication when hardware-backed registration is enabled.
• Fixed trailing whitespace in BIOS serial numbers causing serial-number and client-certificate device posture checks to fail.
• Fixed the client UI crashing at startup when it could not write to the Windows registry.
• Fixed a client UI crash that could occur when the daemon connection was reset during an IPC request.
• Fixed a startup crash when date formatting data for the system locale had not yet loaded.

Known issues

• A Windows DNS client regression may cause connectivity check failures on systems containing large hosts files. While this release includes a fix to mitigate this issue, users may still experience reduced DNS performance and connectivity check failures.

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.
• Fixed the client reconnecting while Emergency Disconnect was active after switching organizations or re-registering.
• Fixed the client being unable to connect after an upgrade when its stored registration credentials no longer matched its configuration.
• Fixed the client service restarting unexpectedly when it was slow to respond, such as after waking from sleep.
• Fixed the client window not appearing on first launch after a fresh install on RHEL 10.
• Fixed duplicate WARP routing policy rules accumulating on reconnect.
• Fixed slow captive portal checks causing the client service to become unresponsive or restart while connecting.
• Fixed a race when switching tunnel protocols during key rotation that could prevent WireGuard from connecting.
• Fixed the client continuing to report “No network” after a successful manual disconnect.
• Fixed a client UI crash that could occur when the daemon connection was reset during an IPC request.
• Fixed a startup crash when date formatting data for the system locale had not yet loaded.

Known issues

• When in DNS Only mode, the client may send DNS queries for names that are configured for Local Domain Fallback to the encrypted DNS server instead of falling back to the system configuration. Local Domain Fallback works as expected in other client modes.

Log Explorer datasets are now queried from the Logs page under Observability in the Cloudflare dashboard. The Logs page brings Log Explorer and Workers Observability datasets together with a shared filter builder, SQL editor, and visualizations.

As part of this change, the Log Explorer menu is no longer shown in the dashboard navigation.

• Your enabled datasets, saved queries, and SQL queries continue to work on the Logs page.
• To manage datasets, open the dataset selector on the Logs page and select Configure next to the Log Explorer datasets.
• The previous Log Search page remains available at its direct URL.

For more information, refer to Log Search and the Logs overview.

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.

AI Gateway's REST API now returns consistent responses when an AI provider rejects credentials. The change applies to POST /ai/run ↗︎.

Update applications that handle AI Gateway REST API errors to treat HTTP 401 as an invalid or rejected provider credential.

For details about providing provider credentials, refer to Bring your own provider keys.

The DNS records page in the Cloudflare dashboard now shows a warning once you have used 85% of your DNS records quota.

The warning reflects the quota that applies to you. If your zone has its own quota, the warning shows that zone's usage. If your account uses an account-level DNS records quota, the warning shows your usage across all zones in the account.

This release introduces a new detection to mitigate a heap-based buffer overflow vulnerability in F5 BIG-IP, and enhances existing command injection protections by incorporating tested beta logic into the baseline rule.

Key Findings

• CVE-2026-94127: A heap-based buffer overflow vulnerability in F5 BIG-IP. Attackers can exploit this flaw to execute arbitrary code on the affected system.

Cloudflare CASB now supports custom finding types, giving security teams full control over the security conditions CASB detects across their SaaS and cloud integrations.

In addition to CASB's library of standard finding types, you can now write your own detection logic using Rego ↗︎, the open-source policy language from Open Policy Agent (OPA). Use custom finding types to match your organization's own thresholds and exceptions, such as flagging admin accounts without two-factor authentication, and get higher-confidence findings to act on.

• Write your own detection logic — Define exactly what CASB flags using Rego expressions evaluated against asset data from your connected integrations.
• Target any supported provider and asset class — Scope a custom finding type to a provider (such as Google Workspace or Microsoft 365) and asset class (such as users, files, or groups), and apply it to all integrations for that provider or a selected subset.
• Built-in validation — Select Validate to check your expression for syntax errors and schema issues before you create the finding type.
• Inspect and duplicate standard finding types — Open any standard finding type to view its detection logic, then duplicate it as the starting point for a custom finding type.
• Works with CASB policies — Use custom finding types in CASB remediation policies to send matching findings to Slack, ServiceNow, or any other webhook destination.

1. In Cloudflare One ↗︎, go to Cloud & SaaS findings > Findings library.
2. Select Create finding.
3. Enter a name, description, and severity.
4. Select a provider and asset class, then set the integration scope.
5. Write your Rego expression and select Validate.
6. Select Create finding.

CASB evaluates the custom finding type against assets as they are created or updated within the selected scope. Matching assets appear as posture finding instances under Posture Findings.

• Learn how to create and manage custom finding types in Cloudflare One.
• Learn how to manage findings in Cloudflare One.
• Learn how to create and manage CASB remediation policies in Cloudflare One.

CASB custom finding types are now available in Cloudflare One.

BGP peering over IPsec and GRE tunnels is generally available for Cloudflare WAN and Magic Transit. You can use it for production workloads.

BGP peering exchanges routes dynamically between your devices and your Cloudflare virtual network routing table. You no longer need to update static routes manually as your network changes.

BGP over IPsec and GRE tunnels is available to all accounts that use Unified Routing. No enablement is required. BGP over CNI remains in closed beta.

For configuration details, refer to:

• Configure BGP routes for Cloudflare WAN
• Configure BGP routes for Magic Transit

Web Search API is now available in beta. Web Search API lets your AI agents and applications search the Internet and ground their responses in live information, instead of guessing URLs or relying on a model's training cutoff.

At launch, you can choose between three search providers: Ceramic.ai, Exa, and Linkup. All three support Zero Data Retention for requests made through Cloudflare, and all have committed to Cloudflare's verified bot crawling standards.

Web Search API runs through AI Gateway, so search requests appear in your gateway logs and are billed to your AI Gateway credits at each provider's list API price, with no additional markup. You can also bring your own provider API key.

Call Web Search API with the REST API:

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/websearch/ \
  --request POST \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
    "query": "What are some fun things to do in Salt Lake City as fall approaches?",
    "provider": "ceramic",
    "limit": 5,
    "options": { "gateway": { "id": "default" } }
  }'

Or from a Worker with the AI binding:

const response = await env.AI.websearch({
	gatewayId: "default",
	query: "What are some fun things to do in Salt Lake City as fall approaches?",
	provider: "exa",
	limit: 5,
});

const results = await response.json();

To get started, refer to How to use Web Search API.

The strict service token authentication setting applies consistent behavior to requests made with service tokens. When the setting is on for a Zero Trust organization, Access handles requests with service token headers as follows:

• If authentication or authorization fails, Access always returns 401 or 403 instead of redirecting the client to the login page with 302.
• Only Service Auth policies can authorize the request. Access ignores Allow policies and any CF_Authorization cookie sent with the request.
• Access does not return a CF_Authorization cookie to the client after successful authentication. Subsequent requests should continue to use service token headers.
• Failed requests for recognized service tokens appear in Access authentication logs.

Zero Trust organizations created on or after October 5, 2026 have strict service token authentication turned on by default and cannot turn it off. Cloudflare recommends that existing organizations turn it on as well.

Organizations created before October 5, 2026 can configure the setting in the dashboard or through the API.

curl "https://api.cloudflare.com/client/v4/accounts/%7Baccount_id%7D/access/organizations" \
	--request PATCH \
	--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
	--json '{
		"strict_service_token_auth": true
	}'

For behavior and configuration details, refer to Strict service token authentication.

The Agents SDK now provides first-class support for building agents using the Pi harness. You can build long-running agents using the combination of Pi 1.0 ↗︎, Pi Durable ↗︎, and the new PiHarness class that the Cloudflare Agents SDK provides, ensuring your agent's work is durably persisted, even if interrupted mid-turn.

Built with Earendil ↗︎, this integration is our first step toward first-class support for third-party agent harnesses on Cloudflare.

Copy promptPrompt copied!

PiHarness is a new "Lifecycle capability" provided by the Cloudflare Agents SDK. Pi Durable provides the agent harness and the Lifecycle is responsible for keeping the agent running in the Durable Object. The Lifecycle is a core concept in the Agents SDK ensuring that long-running work can run in a Durable Object, surviving restarts, crashes, and network issues. We will share more on Lifecycle capabilities in the near future.

npm i agents@latest @earendil-works/pi-durable @earendil-works/pi-ai

yarn add agents@latest @earendil-works/pi-durable @earendil-works/pi-ai

pnpm add agents@latest @earendil-works/pi-durable @earendil-works/pi-ai

bun add agents@latest @earendil-works/pi-durable @earendil-works/pi-ai

Both Pi packages are optional peer dependencies of agents, so you only install them if you use the harness.

Creating a Pi agent requires configuring the Pi Harness with a model, skills, and tools, then registering the PiHarness with the Agent class.

import { Agent } from "agents";
import { createModels } from "@earendil-works/pi-ai/models";
import { createRegistry, Harness } from "@earendil-works/pi-durable";
import { PiHarness } from "agents/harness/pi";
import { createAI } from "agents/models/pi-ai";

export class Assistant extends Agent {
	ai = createAI({ binding: this.env.AI });
	registry = createRegistry();

	harness = new PiHarness({
		harness: ({ storage, context }) => {
			const models = createModels();
			models.setProvider(this.ai.provider);
			return Harness.open(
				storage,
				{ models, registry: this.registry },
				context,
			);
		},
		defaults: { model: this.ai("@cf/moonshotai/kimi-k2.7-code") },
	});

	constructor(ctx, env) {
		super(ctx, env);
		this.lifecycle.use(this.harness);
	}

	async ask(prompt) {
		const { text } = await this.harness.prompt(prompt);
		return text;
	}
}

import { Agent } from "agents";
import { createModels } from "@earendil-works/pi-ai/models";
import { createRegistry, Harness } from "@earendil-works/pi-durable";
import { PiHarness } from "agents/harness/pi";
import { createAI } from "agents/models/pi-ai";

export class Assistant extends Agent<Env> {
	ai = createAI({ binding: this.env.AI });
	registry = createRegistry();

	harness = new PiHarness({
		harness: ({ storage, context }) => {
			const models = createModels();
			models.setProvider(this.ai.provider);
			return Harness.open(
				storage,
				{ models, registry: this.registry },
				context,
			);
		},
		defaults: { model: this.ai("@cf/moonshotai/kimi-k2.7-code") },
	});

	constructor(ctx: DurableObjectState, env: Env) {
		super(ctx, env);
		this.lifecycle.use(this.harness);
	}

	async ask(prompt: string) {
		const { text } = await this.harness.prompt(prompt);
		return text;
	}
}

The agents/models/pi-ai entry point supports AI Gateway and Workers AI models, so you can get started with Cloudflare models right away or use your existing Pi AI provider.

Both tools and system prompt sections are provided to the Pi Harness via extensions.

import { Type } from "@earendil-works/pi-ai";

import { skills } from "agents/harness/pi";

const WordCount = Type.Object({ text: Type.String() });

const wordCount = {
	name: "word_count",
	description: "Count the words in a text.",
	parameters: WordCount,
	replay: "safe",
	async execute({ text }) {
		const words = text.split(/\s+/).filter(Boolean).length;
		return { content: [{ type: "text", text: String(words) }] };
	},
};

// In the harness factory, before Harness.open():
registry.install({
	name: "editor",
	sections: [
		{ key: "preamble", render: () => "You are an editor.", tag: false },
	],
	tools: [wordCount],
});
registry.install(await skills(sources));

import { Type } from "@earendil-works/pi-ai";
import type { ToolRegistration } from "@earendil-works/pi-durable";
import { skills } from "agents/harness/pi";

const WordCount = Type.Object({ text: Type.String() });

const wordCount: ToolRegistration<typeof WordCount> = {
	name: "word_count",
	description: "Count the words in a text.",
	parameters: WordCount,
	replay: "safe",
	async execute({ text }) {
		const words = text.split(/\s+/).filter(Boolean).length;
		return { content: [{ type: "text", text: String(words) }] };
	},
};

// In the harness factory, before Harness.open():
registry.install({
	name: "editor",
	sections: [
		{ key: "preamble", render: () => "You are an editor.", tag: false },
	],
	tools: [wordCount],
});
registry.install(await skills(sources));

For more information on creating and configuring extensions, refer to Extensions.

• Pi harness documentation
• Pi harness extensions
• pi-ai model provider
• Pi harness example ↗︎, with WebSockets, a browser UI, and a @cloudflare/computer Workspace for the model's tools
• Lifecycle ↗︎
• Pi Durable announcement ↗︎ from Earendil

Every plan now gets at least 30 days of analytics data. Adaptive analytics datasets, such as HTTP requests, security events, and DNS analytics, retain at least 31 days of data for Free and Pro domains, and you can query up to 30 days in a single request. Previously, Free and Pro domains could see between 24 hours and 8 days of history depending on the dataset.

A full month of history lets you investigate an issue after it happens, compare today with the same day in previous weeks, and tell a one-time spike from a longer trend. The change applies in the Cloudflare dashboard, in Custom Dashboards, and through the GraphQL Analytics API.

Domain analytics also now live in one place. In the Cloudflare dashboard, select a domain and go to Analytics to see Traffic, Performance, Security, Cache, Origin, DNS, and Visitors as tabs that share one time range and one set of filters. Account-level analytics are under Observability > Analytics.

This change does not alter which datasets or fields your plan can access. Aggregated datasets, such as httpRequests1hGroups, keep their existing per-plan limits. To check the exact retention and query window for a zone or account, query the settings for each dataset.

For plan-specific limits, refer to Security Analytics, Security Events, and GraphQL Analytics API limits.

You can now build Custom Dashboards charts from Workers Observability data. Two new datasets, Workers Observability — Logs and Workers Observability — Traces (OTel), let you chart Worker invocations, log levels, errors, CPU and wall time, span counts, and durations next to HTTP traffic, security events, and other analytics datasets.

This gives you one dashboard for an application that spans Cloudflare's network and your Workers. For example, you can put request volume, WAF blocks, and Worker error rates on the same view, filter all three by time range, and spot whether a spike in errors lines up with a change in traffic.

The datasets are available for every Worker in your account that has Workers Logs or Workers Traces turned on. Custom Dashboards also now allow up to 100 dashboards for every account.

To get started, refer to Workers Observability data in Custom Dashboards.

You can create D1 databases with the us jurisdiction. These databases run and persist data within the United States.

Use this option for regional data residency requirements.

To create a database with the us jurisdiction, run:

npx wrangler@latest d1 create db-with-us-jurisdiction --jurisdiction=us

For more information, refer to D1 data location.

Cloudflare Organizations now support up to 20,000 accounts and 200,000 zones. For MSSP/Distributors using sub-organizations, these limits are applied at the root Organization.

If you require a higher limit, reach out to your account team. The new limits apply to enterprise and MSSP/Distributor Organizations. Legacy reseller partner and brand partner tenants retain their existing quota behavior.

For more information, refer to Account and zone limits.

Jurisdictions for Workers KV namespaces are now generally available. When you create a namespace, you can set a jurisdiction to make sure the namespace's data is only durably stored within that region. Jurisdictions can help you comply with data localization regulations such as GDPR or FedRAMP. Supported jurisdictions are eu, us, and fedramp.

A jurisdiction can only be set when a namespace is created, using the Cloudflare dashboard, Wrangler, the cf CLI, or the REST API, and cannot be added or changed afterwards.

npx wrangler@latest kv namespace create <NAMESPACE_NAME> --jurisdiction=eu

cf kv namespaces create --title <NAMESPACE_NAME> --jurisdiction eu

curl "https://api.cloudflare.com/client/v4/accounts/$ACCOUNT_ID/storage/kv/namespaces" \
  --request POST \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
    "title": "<NAMESPACE_NAME>",
    "jurisdiction": "eu"
  }'

Workers can still access a namespace restricted to a jurisdiction from anywhere in the world, and KV data can be cached outside the jurisdiction on Cloudflare's network. The jurisdiction only controls where the namespace's data is durably stored.

To learn more, refer to Data location.

hash_in_range() is globally available for HTTP products on all plans. It hashes fields into an integer within a specified range. Use this result to select a portion of requests.

Use cf.random_seed to select approximately 10% of requests at random:

hash_in_range(0, 100, cf.random_seed) < 10

With Cloudflare for SaaS, use custom metadata to control rollout progression. Define rollout_pct as a custom key for each hostname. Set its value to an integer from 0 to 100. The expression selects approximately that percentage of requests:

hash_in_range(0, 100, cf.random_seed) < coalesce(lookup_json_integer(cf.hostname.metadata, "rollout_pct"), 0)

If rollout_pct is missing, coalesce() supplies 0. The rule then matches no requests.

For details, refer to the hash_in_range() function reference.

You can now restrict who can access a Quick Tunnel. Use the new --allowed-mail flag in cloudflared to require visitors to authenticate with a one-time PIN sent to their email before they reach your local service.

cloudflared tunnel --url http://localhost:8080 --allowed-mail alice@example.com

Previously, anyone with a trycloudflare.com URL could access the service behind it. Protected Quick Tunnels let you share a local development server, webhook receiver, or demo with specific people without creating a Cloudflare account or configuring a domain.

You can allow:

• A single email address: --allowed-mail alice@example.com
• Multiple email addresses, by repeating the flag or using a comma-separated list: --allowed-mail 'alice@example.com,bob@example.com'
• Every address on a domain: --allowed-mail '*@example.com'

Visitors do not need a Cloudflare account. Access ends for everyone when you stop the cloudflared process.

To get started, update cloudflared to the latest version and refer to Restrict access by email.

Meet @cf/cloudflare/clef and @cf/cloudflare/clef-flash, the first models trained by the Cloudflare Workers AI team, available on Workers AI today.

Clef is a decision model, in the same family as Typesafe's Jev ↗︎. Instead of generating text, it reads an input state and a set of typed questions, then returns a probability for every allowed answer. Your agent gets a structured decision it can act on immediately, for example: route the ticket, block the request, or escalate to a human. There is no free-form output to parse and no reasoning tokens to wait for.

Both models are hosted on Workers AI as Clef and Clef-flash. We are also open-sourcing the weights under the Apache 2.0 license on Hugging Face: Clef ↗︎ and Clef-flash ↗︎. Read the launch blog post ↗︎ for the full story, including how we trained them.

We are also launching a reinforcement learning (RL) fine-tuning service to help you tune Clef for your own workloads. Sign up to work with us as a design partner ↗︎.

Clef is designed to be fast so decisions come back in milliseconds. Across our 43 benchmark runs, we achieved speeds where Clef is 2.5x faster than Jev at the median, and Clef-flash 13x faster.

Hosting on Workers AI adds to that speed. Requests run on GPUs across Cloudflare's network, running close to your users, so the network round trip stays short. You can put Clef directly in the request path of your agent, then hand off to an LLM on Workers AI to take action.

Across 10 decision benchmarks, a Clef model scores highest on 7, ahead of Jev and other open decision models. A few highlights:

On Typesafe's own workflow evals, Clef beats Jev in 3 of 4 areas: invoice processing, customer service, and security incidents. The full results are on the Hugging Face model card ↗︎.

Clef follows the System One API, so you can switch an existing Jev integration to Clef by changing the endpoint and model. Ask up to 64 questions per request, in three types:

• noul: A yes/no question. Returns the probability that the answer is yes.
• choice: Pick one option from a set you define. Returns the chosen option, a probability per option, and a confidence value.
• score: Rate against an ordered rubric. Returns a probability-weighted score and a probability per level.

const response = await env.AI.run("@cf/cloudflare/clef", {
	model: "clef",
	state: "Checkout has been failing for every customer for the last hour.",
	questions: {
		urgent: {
			type: "noul",
			instructions: "Is this support request urgent?",
		},
		team: {
			type: "choice",
			instructions: "Which team should handle this request?",
			criteria: {
				billing: "Payments, invoices, and refunds",
				technical: "Outages, errors, and configuration",
				sales: "Plans and upgrades",
			},
		},
	},
});

// response.answers.urgent.noul -> probability the request is urgent
// response.answers.team.choice -> highest-probability team

const response = await env.AI.run("@cf/cloudflare/clef", {
	model: "clef",
	state: "Checkout has been failing for every customer for the last hour.",
	questions: {
		urgent: {
			type: "noul",
			instructions: "Is this support request urgent?",
		},
		team: {
			type: "choice",
			instructions: "Which team should handle this request?",
			criteria: {
				billing: "Payments, invoices, and refunds",
				technical: "Outages, errors, and configuration",
				sales: "Plans and upgrades",
			},
		},
	},
});

// response.answers.urgent.noul -> probability the request is urgent
// response.answers.team.choice -> highest-probability team

• Support triage: Decide whether a ticket is urgent and which team owns it, then route it without a human in the loop.
• Threat intelligence: Classify a website by category. Paired with Browser Run, Clef fetched, rendered, and classified a domain in 2.2 seconds, compared to 4.7 seconds for gpt-oss-120b in the same workflow.
• Trust and safety: Score user submissions against your own policy rubric and act on the probability.
• Agent guardrails: Let an agent check "should I take this action?" in tens of milliseconds before calling a tool.
• Visual classification: Pass up to four images alongside the state. Unlike text-only decision models, Clef has a vision encoder.

Use Clef through the Workers AI binding (env.AI.run()) or the REST API at /ai/run. You can also use AI Gateway with these endpoints.

For more information, refer to the Clef model page, the Clef-flash model page, and pricing.

@cloudflare/workers-oauth-provider ↗︎ is now v1, with a new split API. One Worker acts as the authorization server: it signs users in and issues tokens. Your MCP server acts as the resource server, and can run in another Worker. It validates each token with the authorization server over a Service Binding, without crossing the public Internet.

• It supports the MCP 2026-07-28 authorization specification ↗︎, including Client ID Metadata Documents ↗︎ and issuer identification ↗︎. It still works with older clients, including those using Dynamic Client Registration ↗︎.
• insufficientScope() gives you step-up authorization ↗︎ in one line.
• The authorization server and the resource server can run in different Workers ↗︎ with different WAF and rate limiting rules.
• One authorization server can issue tokens for many MCP servers ↗︎.
• A migration skill ↗︎ ships in the npm package so a coding agent can perform the upgrade.

import {
	OAuthAuthorizationServer,
	OAuthResourceServer,
	insufficientScope,
} from "@cloudflare/workers-oauth-provider";
import { WorkerEntrypoint } from "cloudflare:workers";

// auth-server Worker: signs users in and issues tokens for both MCP servers.
const authorizationServer = new OAuthAuthorizationServer({
	issuer: "https://auth.example.com",
	resources: [
		"https://calendar.example.com/mcp",
		"https://drive.example.com/mcp",
	],
	scopesSupported: ["calendar:read", "calendar:write", "offline_access"],
	clientIdMetadataDocumentEnabled: true,
});

export class AuthServer extends WorkerEntrypoint {
	fetch(request) {
		if (new URL(request.url).pathname === "/authorize") {
			return showConsent(request, this.env);
		}
		return authorizationServer.fetch(request, this.env, this.ctx);
	}

	validateToken(resource, token) {
		return authorizationServer.validateToken(resource, token, this.env);
	}
}

// calendar MCP Worker: checks tokens with AuthServer over a Service Binding.
export const calendar = new OAuthResourceServer({
	resourceMetadata: {
		resource: "https://calendar.example.com/mcp",
		authorization_servers: ["https://auth.example.com"],
	},
	requiredScopes: ["calendar:read"],
	validateToken: (env) => env.AUTH_SERVER.validateToken,
	handler: {
		fetch(request, env, ctx) {
			if (
				request.method === "POST" &&
				!ctx.auth.scope.includes("calendar:write")
			) {
				return insufficientScope(ctx.auth, ["calendar:read", "calendar:write"]);
			}
			return handleMcp(request, ctx.props);
		},
	},
});

import {
	OAuthAuthorizationServer,
	OAuthResourceServer,
	insufficientScope,
} from "@cloudflare/workers-oauth-provider";
import { WorkerEntrypoint } from "cloudflare:workers";

// auth-server Worker: signs users in and issues tokens for both MCP servers.
const authorizationServer = new OAuthAuthorizationServer<Env>({
	issuer: "https://auth.example.com",
	resources: [
		"https://calendar.example.com/mcp",
		"https://drive.example.com/mcp",
	],
	scopesSupported: ["calendar:read", "calendar:write", "offline_access"],
	clientIdMetadataDocumentEnabled: true,
});

export class AuthServer extends WorkerEntrypoint<Env> {
	fetch(request: Request) {
		if (new URL(request.url).pathname === "/authorize") {
			return showConsent(request, this.env);
		}
		return authorizationServer.fetch(request, this.env, this.ctx);
	}

	validateToken(resource: string, token: string) {
		return authorizationServer.validateToken(resource, token, this.env);
	}
}

// calendar MCP Worker: checks tokens with AuthServer over a Service Binding.
export const calendar = new OAuthResourceServer<Env, AuthProps>({
	resourceMetadata: {
		resource: "https://calendar.example.com/mcp",
		authorization_servers: ["https://auth.example.com"],
	},
	requiredScopes: ["calendar:read"],
	validateToken: (env) => env.AUTH_SERVER.validateToken,
	handler: {
		fetch(request, env, ctx) {
			if (
				request.method === "POST" &&
				!ctx.auth.scope.includes("calendar:write")
			) {
				return insufficientScope(ctx.auth, ["calendar:read", "calendar:write"]);
			}
			return handleMcp(request, ctx.props);
		},
	},
});

In the example, env.AUTH_SERVER.validateToken is that Service Binding call. The calendar Worker needs no KV namespace of its own.

{
	"name": "calendar-mcp",
	"main": "src/index.ts",
	// Set this to today's date
	"compatibility_date": "2026-10-07",
	"services": [
		{
			"binding": "AUTH_SERVER",
			"service": "auth-server",
			"entrypoint": "AuthServer",
		},
	],
}

name = "calendar-mcp"
main = "src/index.ts"
# Set this to today's date
compatibility_date = "2026-10-07"

[[services]]
binding = "AUTH_SERVER"
service = "auth-server"
entrypoint = "AuthServer"

OAuthResourceServer publishes the RFC 9728 ↗︎ protected resource metadata that MCP clients use to find your authorization server. It answers requests without a token with a 401 challenge that points to that metadata. It also rejects tokens issued for any other resource.

You can still use OAuthProvider as both the authorization server and the MCP server. For most 0.x deployments, the only required change is to add resourceMetadata: { resource }.

• Consent page ↗︎ and upstream sign-in ↗︎ helpers implement the MCP confused deputy protections.
• Sliding refresh token expiry ↗︎ with refreshTokenIdleTTL.
• Resumable KV cleanup ↗︎ with purgeExpiredData().
• An internal reason ↗︎ on every error passed to onError.

npm i @cloudflare/workers-oauth-provider@latest

yarn add @cloudflare/workers-oauth-provider@latest

pnpm add @cloudflare/workers-oauth-provider@latest

bun add @cloudflare/workers-oauth-provider@latest

Point your coding agent at node_modules/@cloudflare/workers-oauth-provider/skills/migrate-to-1.0/SKILL.md, or follow the migration guide ↗︎.

For both Workers in full, refer to the split Workers example ↗︎.

AI Search is now generally available. Usage-based billing begins on November 1, 2026, with included monthly ingestion, storage, semantic query, and full-text query usage. Cloudflare will send a reminder email the week before billing begins.

Refer to Limits & pricing for rates and included usage.

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 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.

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.

Optical character recognition (OCR) is available on every account for scanned PDFs. Plain-text or code files and PDFs with OCR enabled can be up to 10 MiB. PDFs without OCR and other supported formats remain limited to 4 MiB.

Refer to Data source for file limits and Limits & pricing for OCR pricing.

When you create an AI Search instance, the type field is optional. AI Search infers a website source from an HTTP or HTTPS URL, or an R2 source from an existing bucket name.

Refer to Data source for details.

Artifacts, Cloudflare's versioned file system that speaks Git, is now in open beta. Artifacts is built for scale, so you can create a repository per project, user, session, or task.

With Artifacts, you can:

• Deploy repositories to Workers — Connect an Artifacts repository through Workers Builds. Pushes to the production branch deploy the updated Worker, while other branches create or update Worker Previews.
• Programmatically manage repositories — Use an Artifacts binding from a Worker to create or fork repos, inspect files and commits, read files by path, and issue repo-scoped Git tokens.
• React to repository changes — Subscribe to events when a repository is created, imported, forked, deleted, pushed to, cloned, or fetched.
• Control where repository data is stored — Choose to store and process your data in the US or EU.
• Monitor repository usage — View total operations, pulls, pushes, errors, and error rates in the Cloudflare dashboard or via API for analytics.

Artifacts is available for customers on the Workers Paid plan. Cloudflare will begin billing for Artifacts on October 14, 2026.

We are hosting a competition to see who can build the next GitHub on Cloudflare using Workers and Artifacts.

Apply today ↗︎ — submissions are open until October 14, 2026.

The first-place team will receive $25,000 in Cloudflare credits. The top three teams will be flown to San Francisco to present what they built at Cloudflare Connect.

Get started with the Artifacts documentation.