Changelog

Cloudflare Gateway now supports OIDC Claims as a selector in Firewall, Resolver, and Egress policies. Administrators can use custom OIDC claims from their identity provider to build fine-grained, identity-based traffic policies across all Gateway policy types.

With this update, you can:

• Filter traffic in DNS, HTTP, and Network firewall policies based on OIDC claim values.
• Apply custom resolver policies to route DNS queries to specific resolvers depending on a user's OIDC claims.
• Control egress policies to assign dedicated egress IPs based on OIDC claim attributes.

For example, you can create a policy that routes traffic differently for users with department=engineering in their OIDC claims, or restrict access to certain destinations based on a user's role claim.

To get started, configure custom OIDC claims on your identity provider and use the OIDC Claims selector in the Gateway policy builder.

For more information, refer to Identity-based policies.

The top-level Interconnects page in the Cloudflare dashboard has been removed. Interconnects are now located under Connectors > Interconnects.

Your existing configurations and functionality remain the same.

Dynamic Workers are now in open beta ↗ for all paid Workers users. You can now have a Worker spin up other Workers, called Dynamic Workers, at runtime to execute code on-demand in a secure, sandboxed environment. Dynamic Workers start in milliseconds, making them well suited for fast, secure code execution at scale.

• Code Mode: LLMs are trained to write code. Run tool-calling logic written in code instead of stepping through many tool calls, which can save up to 80% in inference tokens and cost.
• AI agents executing code: Run code for tasks like data analysis, file transformation, API calls, and chained actions.
• Running AI-generated code: Run generated code for prototypes, projects, and automations in a secure, isolated sandboxed environment.
• Fast development and previews: Load prototypes, previews, and playgrounds in milliseconds.
• Custom automations: Create custom tools on the fly that execute a task, call an integration, or automate a workflow.

Dynamic Workers support two loading modes:

• load(code) — for one-time code execution (equivalent to calling get() with a null ID).
• get(id, callback) — caches a Dynamic Worker by ID so it can stay warm across requests. Use this when the same code will receive subsequent requests.

export default {
	async fetch(request, env) {
		const worker = env.LOADER.load({
			compatibilityDate: "2026-01-01",
			mainModule: "src/index.js",
			modules: {
				"src/index.js": `
					export default {
						fetch() {
							return new Response("Hello from a dynamic Worker");
						},
					};
				`,
			},
			// Block all outbound network access from the Dynamic Worker.
			globalOutbound: null,
		});

		return worker.getEntrypoint().fetch(request);
	},
};

export default {
	async fetch(request: Request, env: Env): Promise<Response> {
		const worker = env.LOADER.load({
			compatibilityDate: "2026-01-01",
			mainModule: "src/index.js",
			modules: {
				"src/index.js": `
					export default {
						fetch() {
							return new Response("Hello from a dynamic Worker");
						},
					};
				`,
			},
			// Block all outbound network access from the Dynamic Worker.
			globalOutbound: null,
		});

		return worker.getEntrypoint().fetch(request);
	},
};

Here are 3 new libraries to help you build with Dynamic Workers:

• @cloudflare/codemode ↗: Replace individual tool calls with a single code() tool, so LLMs write and execute TypeScript that orchestrates multiple API calls in one pass.

• @cloudflare/worker-bundler ↗: Resolve npm dependencies and bundle source files into ready-to-load modules for Dynamic Workers, all at runtime.

• @cloudflare/shell ↗: Give your agent a virtual filesystem inside a Dynamic Worker with persistent storage backed by SQLite and R2.

Dynamic Workers Starter

Use this starter ↗ to deploy a Worker that can load and execute Dynamic Workers.

Dynamic Workers Playground

Deploy the Dynamic Workers Playground ↗ to write or import code, bundle it at runtime with @cloudflare/worker-bundler, execute it through a Dynamic Worker, and see real-time responses and execution logs.

For the full API reference and configuration options, refer to the Dynamic Workers documentation.

Dynamic Workers pricing is based on three dimensions: Dynamic Workers created daily, requests, and CPU time.

¹ Uses Workers Standard rates and will appear as part of your existing Workers bill, not as separate Dynamic Workers charges.

Note: Dynamic Workers requests and CPU time are already billed as part of your Workers plan and will count toward your Workers requests and CPU usage. The Dynamic Workers created daily charge is not yet active — you will not be billed for the number of Dynamic Workers created at this time. Pricing information is shared in advance so you can estimate future costs.

Workflow instance methods pause(), resume(), restart(), and terminate() are now available in local development when using wrangler dev.

You can now test the full Workflow instance lifecycle locally:

const instance = await env.MY_WORKFLOW.create({
	id: "my-instance-id",
});

await instance.pause(); // pauses a running workflow instance
await instance.resume(); // resumes a paused instance
await instance.restart(); // restarts the instance from the beginning
await instance.terminate(); // terminates the instance immediately

The latest release of the Agents SDK ↗ exposes agent state as a readable property, prevents duplicate schedule rows across Durable Object restarts, brings full TypeScript inference to AgentClient, and migrates to Zod 4.

Both useAgent (React) and AgentClient (vanilla JS) now expose a state property that reflects the current agent state. Previously, reading state required manually tracking it through the onStateUpdate callback.

React (useAgent)

const agent = useAgent({
	agent: "game-agent",
	name: "room-123",
});

// Read state directly — no separate useState + onStateUpdate needed
return <div>Score: {agent.state?.score}</div>;

// Spread for partial updates
agent.setState({ ...agent.state, score: (agent.state?.score ?? 0) + 10 });

const agent = useAgent<GameAgent, GameState>({
	agent: "game-agent",
	name: "room-123",
});

// Read state directly — no separate useState + onStateUpdate needed
return <div>Score: {agent.state?.score}</div>;

// Spread for partial updates
agent.setState({ ...agent.state, score: (agent.state?.score ?? 0) + 10 });

agent.state is reactive — the component re-renders when state changes from either the server or a client-side setState() call.

Vanilla JS (AgentClient)

const client = new AgentClient({
	agent: "game-agent",
	name: "room-123",
	host: "your-worker.workers.dev",
});

client.setState({ score: 100 });
console.log(client.state); // { score: 100 }

const client = new AgentClient<GameAgent>({
	agent: "game-agent",
	name: "room-123",
	host: "your-worker.workers.dev",
});

client.setState({ score: 100 });
console.log(client.state); // { score: 100 }

State starts as undefined and is populated when the server sends the initial state on connect (from initialState) or when setState() is called. Use optional chaining (agent.state?.field) for safe access. The onStateUpdate callback continues to work as before — the new state property is additive.

schedule() now supports an idempotent option that deduplicates by (type, callback, payload), preventing duplicate rows from accumulating when called in places that run on every Durable Object restart such as onStart().

Cron schedules are idempotent by default. Calling schedule("0 * * * *", "tick") multiple times with the same callback, expression, and payload returns the existing schedule row instead of creating a new one. Pass { idempotent: false } to override.

Delayed and date-scheduled types support opt-in idempotency:

import { Agent } from "agents";

class MyAgent extends Agent {
	async onStart() {
		// Safe across restarts — only one row is created
		await this.schedule(60, "maintenance", undefined, { idempotent: true });
	}
}

import { Agent } from "agents";

class MyAgent extends Agent {
	async onStart() {
		// Safe across restarts — only one row is created
		await this.schedule(60, "maintenance", undefined, { idempotent: true });
	}
}

Two new warnings help catch common foot-guns:

• Calling schedule() inside onStart() without { idempotent: true } emits a console.warn with actionable guidance (once per callback; skipped for cron and when idempotent is set explicitly).
• If an alarm cycle processes 10 or more stale one-shot rows for the same callback, the SDK emits a console.warn and a schedule:duplicate_warning diagnostics channel event.

AgentClient now accepts an optional agent type parameter for full type inference on RPC calls, matching the typed experience already available with useAgent.

const client = new AgentClient({
	agent: "my-agent",
	host: window.location.host,
});

// Typed call — method name autocompletes, args and return type inferred
const value = await client.call("getValue");

// Typed stub — direct RPC-style proxy
await client.stub.getValue();
await client.stub.add(1, 2);

const client = new AgentClient<MyAgent>({
	agent: "my-agent",
	host: window.location.host,
});

// Typed call — method name autocompletes, args and return type inferred
const value = await client.call("getValue");

// Typed stub — direct RPC-style proxy
await client.stub.getValue();
await client.stub.add(1, 2);

State is automatically inferred from the agent type, so onStateUpdate is also typed:

const client = new AgentClient({
	agent: "my-agent",
	host: window.location.host,
	onStateUpdate: (state) => {
		// state is typed as MyAgent's state type
	},
});

const client = new AgentClient<MyAgent>({
	agent: "my-agent",
	host: window.location.host,
	onStateUpdate: (state) => {
		// state is typed as MyAgent's state type
	},
});

Existing untyped usage continues to work without changes. The RPC type utilities (AgentMethods, AgentStub, RPCMethods) are now exported from agents/client for advanced typing scenarios. agents, @cloudflare/ai-chat, and @cloudflare/codemode now require zod ^4.0.0. Zod v3 is no longer supported.

• Turn serialization — onChatMessage() and _reply() work is now queued so user requests, tool continuations, and saveMessages() never stream concurrently.
• Duplicate messages on stop — Clicking stop during an active stream no longer splits the assistant message into two entries.
• Duplicate messages after tool calls — Orphaned client IDs no longer leak into persistent storage.

keepAlive() now uses a lightweight in-memory ref count instead of schedule rows. Multiple concurrent callers share a single alarm cycle. The @experimental tag has been removed from both keepAlive() and keepAliveWhile().

A new entry point @cloudflare/codemode/tanstack-ai adds support for TanStack AI's ↗ chat() as an alternative to the Vercel AI SDK's streamText():

import {
	createCodeTool,
	tanstackTools,
} from "@cloudflare/codemode/tanstack-ai";
import { chat } from "@tanstack/ai";

const codeTool = createCodeTool({
	tools: [tanstackTools(myServerTools)],
	executor,
});

const stream = chat({ adapter, tools: [codeTool], messages });

import { createCodeTool, tanstackTools } from "@cloudflare/codemode/tanstack-ai";
import { chat } from "@tanstack/ai";

const codeTool = createCodeTool({
	tools: [tanstackTools(myServerTools)],
	executor,
});

const stream = chat({ adapter, tools: [codeTool], messages });

To update to the latest version:

npm i agents@latest @cloudflare/ai-chat@latest

AI Search now offers new REST API endpoints for search and chat that use an OpenAI compatible format. This means you can use the familiar messages array structure that works with existing OpenAI SDKs and tools. The messages array also lets you pass previous messages within a session, so the model can maintain context across multiple turns.

Here is an example request to the Chat Completions endpoint using the new messages array format:

curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai-search/instances/{NAME}/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {API_TOKEN}" \
  -d '{
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful documentation assistant."
      },
      {
        "role": "user",
        "content": "How do I get started?"
      }
    ]
  }'

For more details, refer to the AI Search REST API guide.

If you are using the previous AutoRAG API endpoints (/autorag/rags/), we recommend migrating to the new endpoints. The previous AutoRAG API endpoints will continue to be fully supported.

Refer to the migration guide for step-by-step instructions.

AI Search now supports public endpoints, UI snippets, and MCP, making it easy to add search to your website or connect AI agents.

Public endpoints allow you to expose AI Search capabilities without requiring API authentication. To enable public endpoints:

1. Go to AI Search in the Cloudflare dashboard. Go to AI Search ↗
2. Select your instance, and turn on Public Endpoint in Settings. For more details, refer to Public endpoint configuration.

UI snippets are pre-built search and chat components you can embed in your website. Visit search.ai.cloudflare.com ↗ to configure and preview components for your AI Search instance.

To add a search modal to your page:

<script
	type="module"
	src="https://<INSTANCE_ID>.search.ai.cloudflare.com/assets/v0.0.25/search-snippet.es.js"
></script>

<search-modal-snippet
	api-url="https://<INSTANCE_ID>.search.ai.cloudflare.com/"
	placeholder="Search..."
>
</search-modal-snippet>

For more details, refer to the UI snippets documentation.

The MCP endpoint allows AI agents to search your content via the Model Context Protocol. Connect your MCP client to:

https://<INSTANCE_ID>.search.ai.cloudflare.com/mcp

For more details, refer to the MCP documentation.

AI Search now supports custom metadata filtering, allowing you to define your own metadata fields and filter search results based on attributes like category, version, or any custom field you define.

You can define up to 5 custom metadata fields per AI Search instance. Each field has a name and data type (text, number, or boolean):

curl -X POST https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai-search/instances \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {API_TOKEN}" \
  -d '{
    "id": "my-instance",
    "type": "r2",
    "source": "my-bucket",
    "custom_metadata": [
      { "field_name": "category", "data_type": "text" },
      { "field_name": "version", "data_type": "number" },
      { "field_name": "is_public", "data_type": "boolean" }
    ]
  }'

How you attach metadata depends on your data source:

• R2 bucket: Set metadata using S3-compatible custom headers (x-amz-meta-*) when uploading objects. Refer to R2 custom metadata for examples.
• Website: Add <meta> tags to your HTML pages. Refer to Website custom metadata for details.

Use custom metadata fields in your search queries alongside built-in attributes like folder and timestamp:

curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai-search/instances/{NAME}/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {API_TOKEN}" \
  -d '{
    "messages": [
      {
        "content": "How do I configure authentication?",
        "role": "user"
      }
    ],
    "ai_search_options": {
      "retrieval": {
        "filters": {
          "category": "documentation",
          "version": { "$gte": 2.0 }
        }
      }
    }
  }'

Learn more in the metadata filtering documentation.

Two new fields are now available in the httpRequestsAdaptive and httpRequestsAdaptiveGroups GraphQL Analytics API datasets:

• webAssetsOperationId — the ID of the saved endpoint that matched the incoming request.
• webAssetsLabelsManaged — the managed labels mapped to the matched operation at the time of the request (for example, cf-llm, cf-log-in). At most 10 labels are returned per request.

Both fields are empty when no operation matched. webAssetsLabelsManaged is also empty when no managed labels are assigned to the matched operation.

These fields allow you to determine, per request, which Web Assets operation was matched and which managed labels were active. This is useful for troubleshooting downstream security detection verdicts — for example, understanding why AI Security for Apps did or did not flag a request.

Refer to Endpoint labeling service for GraphQL query examples.

R2 SQL now supports an expanded SQL grammar so you can write richer analytical queries without exporting data. This release adds CASE expressions, column aliases, arithmetic in clauses, 163 scalar functions, 33 aggregate functions, EXPLAIN, Common Table Expressions (CTEs),and full struct/array/map access. R2 SQL is Cloudflare's serverless, distributed, analytics query engine for querying Apache Iceberg ↗ tables stored in R2 Data Catalog. This page documents the supported SQL syntax.

• Column aliases — SELECT col AS alias now works in all clauses
• CASE expressions — conditional logic directly in SQL (searched and simple forms)
• Scalar functions — 163 new functions across math, string, datetime, regex, crypto, encoding, and type inspection categories
• Aggregate functions — statistical (variance, stddev, correlation, regression), bitwise, boolean, and positional aggregates join the existing basic and approximate functions
• Complex types — query struct fields with bracket notation, use 46 array functions, and extract map keys/values
• Common table expressions (CTEs) — use WITH ... AS to define named temporary result sets. Chained CTEs are supported. All CTEs must reference the same single table.
• Full expression support — arithmetic, type casting (CAST, TRY_CAST, :: shorthand), and EXTRACT in SELECT, WHERE, GROUP BY, HAVING, and ORDER BY

SELECT source,
    CASE
        WHEN AVG(price) > 30 THEN 'premium'
        WHEN AVG(price) > 10 THEN 'mid-tier'
        ELSE 'budget'
    END AS tier,
    round(stddev(price), 2) AS price_volatility,
    approx_percentile_cont(price, 0.95) AS p95_price
FROM my_namespace.sales_data
GROUP BY source

SELECT product_name,
    pricing['price'] AS price,
    array_to_string(tags, ', ') AS tag_list
FROM my_namespace.products
WHERE array_has(tags, 'Action')
ORDER BY pricing['price'] DESC
LIMIT 10

WITH monthly AS (
    SELECT date_trunc('month', sale_timestamp) AS month,
        department,
        COUNT(*) AS transactions,
        round(AVG(total_amount), 2) AS avg_amount
    FROM my_namespace.sales_data
    WHERE sale_timestamp BETWEEN '2025-01-01T00:00:00Z' AND '2025-12-31T23:59:59Z'
    GROUP BY date_trunc('month', sale_timestamp), department
),
ranked AS (
    SELECT month, department, transactions, avg_amount,
        CASE
            WHEN avg_amount > 1000 THEN 'high-value'
            WHEN avg_amount > 500 THEN 'mid-value'
            ELSE 'standard'
        END AS tier
    FROM monthly
    WHERE transactions > 100
)
SELECT * FROM ranked
ORDER BY month, avg_amount DESC

For the full function reference and syntax details, refer to the SQL reference. For limitations and best practices, refer to Limitations and best practices.

This week's release focuses on new improvements to enhance coverage.

Key Findings

• Existing rule enhancements have been deployed to improve detection resilience against broad classes of web attacks and strengthen behavioral coverage.

Cloudflare Access supports managed OAuth, which allows non-browser clients — such as CLIs, AI agents, SDKs, and scripts — to authenticate with Access-protected applications using a standard OAuth 2.0 authorization code flow.

Previously, non-browser clients that attempted to access a protected application received a 302 redirect to a login page they could not complete. The established workaround was cloudflared access curl, which required installing additional tooling.

With managed OAuth, clients instead receive a 401 response with a WWW-Authenticate header that points to Access's OAuth discovery endpoints (RFC 8414 ↗ and RFC 9728 ↗). The client opens the end user's browser to the Access login page. The end user authenticates with their identity provider, and the client receives an OAuth access token for subsequent requests.

Access enforces the same policies as a browser login; the OAuth layer is a new transport mechanism, not a separate authentication path.

Managed OAuth can be enabled on any self-hosted Access application or MCP server portal. It is opt-in for existing applications to avoid interfering with those that run their own OAuth servers and rely on their own WWW-Authenticate headers.

To enable managed OAuth, go to Zero Trust > Access controls > Applications, edit the application, and turn on Managed OAuth under Advanced settings.

You can also enable it via the API by setting oauth_configuration.enabled to true on the Access applications endpoint.

For setup instructions, refer to Enable managed OAuth.

MCP server portals can now route traffic through Cloudflare Gateway for richer HTTP request logging and data loss prevention (DLP) scanning.

When Gateway routing is turned on, portal traffic appears in your Gateway HTTP logs. You can create Gateway HTTP policies with DLP profiles to detect and block sensitive data sent to upstream MCP servers.

To enable Gateway routing, go to Access controls > AI controls, edit the portal, and turn on Route traffic through Cloudflare Gateway under Basic information.

For more details, refer to Route traffic through Gateway.

DNS Analytics is now available for customers with Customer Metadata Boundary (CMB) set to EU. Query your DNS analytics data while keeping metadata stored in the EU region.

This update includes:

• DNS Analytics — Access the same DNS analytics experience for zones in CMB=EU accounts.
• EU data residency — Analytics data is stored and queried from the EU region, meeting data localization requirements.
• DNS Firewall Analytics — DNS Firewall analytics is now supported for CMB=EU customers.

Available to customers with the Data Localization Suite who have Customer Metadata Boundary configured for the EU region.

• Authoritative DNS: In the Cloudflare dashboard, select your zone and go to the Analytics page.

  Go to Analytics ↗

• DNS Firewall: In the Cloudflare dashboard, go to the DNS Firewall Analytics page.

  Go to Analytics ↗

For more information, refer to DNS Analytics and DNS Firewall Analytics.

In the Cloudflare One dashboard, the overview page for a specific Cloudflare Tunnel now shows all replicas of that tunnel and supports streaming logs from multiple replicas at once.

Previously, you could only stream logs from one replica at a time. With this update:

• Replicas on the tunnel overview — All active replicas for the selected tunnel now appear on that tunnel's overview page under Connectors. Select any replica to stream its logs.
• Multi-connector log streaming — Stream logs from multiple replicas simultaneously, making it easier to correlate events across your infrastructure during debugging or incident response. To try it out, log in to Cloudflare One ↗ and go to Networks > Connectors > Cloudflare Tunnels. Select View logs next to the tunnel you want to monitor.

For more information, refer to Tunnel log streams and Deploy replicas.

Each VPC Service now has a Metrics tab so you can monitor connection health and debug failures without leaving the dashboard.

• Connections — See successful and failed connections over time, broken down by what is responsible: your origin (Bad Upstream), your configuration (Client), or Cloudflare (Internal).
• Latency — Track connection and DNS resolution latency trends.
• Errors — Drill into specific error codes grouped by category, with filters to isolate upstream, client, or internal failures.

You can also view and edit your VPC Service configuration, host details, and port assignments from the Settings tab.

For a full list of error codes and what they mean, refer to Troubleshooting.

Service Key authentication for the Cloudflare API is deprecated. Service Keys will stop working on September 30, 2026.

API Tokens replace Service Keys with fine-grained permissions, expiration, and revocation.

Replace any use of the X-Auth-User-Service-Key header with an API Token scoped to the permissions your integration requires.

If you use cloudflared, update to a version from November 2022 or later. These versions already use API Tokens.

If you use origin-ca-issuer ↗, update to a version that supports API Token authentication.

For more information, refer to API deprecations.

Hyperdrive now supports custom TLS/SSL certificates for MySQL databases, bringing the same certificate options previously available for PostgreSQL to MySQL connections.

You can now configure:

• Server certificate verification with VERIFY_CA or VERIFY_IDENTITY SSL modes to verify that your MySQL database server's certificate is signed by the expected certificate authority (CA).
• Client certificates (mTLS) for Hyperdrive to authenticate itself to your MySQL database with credentials beyond username and password.

Create a Hyperdrive configuration with custom certificates for MySQL:

# Upload a CA certificate
npx wrangler cert upload certificate-authority --ca-cert your-ca-cert.pem --name your-custom-ca-name

# Create a Hyperdrive with VERIFY_IDENTITY mode
npx wrangler hyperdrive create your-hyperdrive-config \
  --connection-string="mysql://user:password@hostname:port/database" \
  --ca-certificate-id <CA_CERT_ID> \
  --sslmode VERIFY_IDENTITY

For more information, refer to SSL/TLS certificates for Hyperdrive and MySQL TLS/SSL modes.

You can now manage Cloudflare Tunnels directly from Wrangler, the CLI for the Cloudflare Developer Platform. The new wrangler tunnel commands let you create, run, and manage tunnels without leaving your terminal.

Available commands:

• wrangler tunnel create — Create a new remotely managed tunnel.
• wrangler tunnel list — List all tunnels in your account.
• wrangler tunnel info — Display details about a specific tunnel.
• wrangler tunnel delete — Delete a tunnel.
• wrangler tunnel run — Run a tunnel using the cloudflared daemon.
• wrangler tunnel quick-start — Start a free, temporary tunnel without an account using Quick Tunnels.

Wrangler handles downloading and managing the cloudflared binary automatically. On first use, you will be prompted to download cloudflared to a local cache directory.

These commands are currently experimental and may change without notice.

To get started, refer to the Wrangler tunnel commands documentation.

Workers AI is officially in the big models game. @cf/moonshotai/kimi-k2.5 is the first frontier-scale open-source model on our AI inference platform — a large model with a full 256k context window, multi-turn tool calling, vision inputs, and structured outputs. By bringing a frontier-scale model directly onto the Cloudflare Developer Platform, you can now run the entire agent lifecycle on a single, unified platform.

The model has proven to be a fast, efficient alternative to larger proprietary models without sacrificing quality. As AI adoption increases, the volume of inference is skyrocketing — now you can access frontier intelligence at a fraction of the cost.

• 256,000 token context window for retaining full conversation history, tool definitions, and entire codebases across long-running agent sessions
• Multi-turn tool calling for building agents that invoke tools across multiple conversation turns
• Vision inputs for processing images alongside text
• Structured outputs with JSON mode and JSON Schema support for reliable downstream parsing
• Function calling for integrating external tools and APIs into agent workflows

When an agent sends a new prompt, it resends all previous prompts, tools, and context from the session. The delta between consecutive requests is usually just a few new lines of input. Prefix caching avoids reprocessing the shared context, saving time and compute from the prefill stage. This means faster Time to First Token (TTFT) and higher Tokens Per Second (TPS) throughput.

Workers AI has done prefix caching, but we are now surfacing cached tokens as a usage metric and offering a discount on cached tokens compared to input tokens (pricing is listed on the model page).

curl -X POST \
  "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/moonshotai/kimi-k2.5" \
  -H "Authorization: Bearer {api_token}" \
  -H "Content-Type: application/json" \
  -H "x-session-affinity: ses_12345678" \
  -d '{
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is prefix caching and why does it matter?"
      }
    ],
    "max_tokens": 2400,
    "stream": true
  }'

Some clients like OpenCode ↗ implement session affinity automatically. The Agents SDK ↗ starter also sets up the wiring for you.

For volumes of requests that exceed synchronous rate limits, you can submit batches of inferences to be completed asynchronously. We have revamped the Asynchronous Batch API with a pull-based system that processes queued requests as soon as capacity is available. With internal testing, async requests usually execute within 5 minutes, but this depends on live traffic.

The async API is the best way to avoid capacity errors in durable workflows. It is ideal for use cases that are not real-time, such as code scanning agents or research agents.

To use the asynchronous API, pass queueRequest: true:

// 1. Push a batch of requests into the queue
const res = await env.AI.run(
	"@cf/moonshotai/kimi-k2.5",
	{
		requests: [
			{
				messages: [{ role: "user", content: "Tell me a joke" }],
			},
			{
				messages: [{ role: "user", content: "Explain the Pythagoras theorem" }],
			},
		],
	},
	{ queueRequest: true },
);

// 2. Grab the request ID
const requestId = res.request_id;

// 3. Poll for the result
const result = await env.AI.run("@cf/moonshotai/kimi-k2.5", {
	request_id: requestId,
});

if (result.status === "queued" || result.status === "running") {
	// Retry by polling again
} else {
	return Response.json(result);
}

You can also set up event notifications to know when inference is complete instead of polling.

Use Kimi K2.5 through the Workers AI binding (env.AI.run()), the REST API at /run or /v1/chat/completions, AI Gateway, or via the OpenAI-compatible endpoint.

For more information, refer to the Kimi K2.5 model page, pricing, and prompt caching.

Cloudflare dashboard SCIM provisioning now supports Authentik ↗ as an identity provider, joining Okta and Microsoft Entra ID as explicitly supported providers.

Customers can now sync users and group information from Authentik to Cloudflare, apply Permission Policies to those groups, and manage the lifecycle of users & groups directly from your Authentik Identity Provider.

For more information:

• SCIM provisioning overview
• Provision with Authentik

Cloudflare dashboard SCIM provisioning operations are now captured in Audit Logs v2, giving you visibility into user and group changes made by your identity provider.

Logged actions:

For more details, refer to the Audit Logs v2 documentation.

The cf.timings.worker_msec field is now available in the Ruleset Engine. This field reports the wall-clock time that a Cloudflare Worker spent handling a request, measured in milliseconds.

You can use this field to identify slow Worker executions, detect performance regressions, or build rules that respond differently based on Worker processing time, such as logging requests that exceed a latency threshold.

Example filter expression:

cf.timings.worker_msec > 500

For more information, refer to the Fields reference.

We are introducing Logo Match Preview, bringing the same pre-save visibility to visual assets that was previously only available for string-based queries. This update allows you to fine-tune your brand detection strategy before committing to a live monitor.

• Upload your brand logo and immediately see a sample of potential matches from recently detected sites before finalizing the query
• Adjust your similarity score (from 75% to 100%) and watch the results refresh in real-time to find the balance between broad detection and noise reduction
• Review the specific logos triggered by your current settings to ensure your query is capturing the right level of brand infringement

If you are ready to test your brand assets, go to the Brand Protection dashboard ↗ to try the new preview tool.

You can now use a Workers binding to transform videos with Media Transformations. This allows you to resize, crop, extract frames, and extract audio from videos stored anywhere, even in private locations like R2 buckets.

The Media Transformations binding is useful when you want to:

• Transform videos stored in private or protected sources
• Optimize videos and store the output directly back to R2 for re-use
• Extract still frames for classification or description with Workers AI
• Extract audio tracks for transcription using Workers AI

To get started, add the Media binding to your Wrangler configuration:

{
  "$schema": "./node_modules/wrangler/config-schema.json",
  "media": {
    "binding": "MEDIA"
  }
}

[media]
binding = "MEDIA"

Then use the binding in your Worker to transform videos:

export default {
	async fetch(request, env) {
		const video = await env.R2_BUCKET.get("input.mp4");

		const result = env.MEDIA.input(video.body)
			.transform({ width: 480, height: 270 })
			.output({ mode: "video", duration: "5s" });

		return await result.response();
	},
};

export default {
	async fetch(request, env) {
		const video = await env.R2_BUCKET.get("input.mp4");

		const result = env.MEDIA.input(video.body)
			.transform({ width: 480, height: 270 })
			.output({ mode: "video", duration: "5s" });

		return await result.response();
	},
};

Output modes include video for optimized MP4 clips, frame for still images, spritesheet for multiple frames, and audio for M4A extraction.

For more information, refer to the Media Transformations binding documentation.