--- title: Developer platform Changelog image: https://edgetunnel-b2h.pages.dev/cf-twitter-card.png --- > Documentation Index > Fetch the complete documentation index at: https://edgetunnel-b2h.pages.dev/changelog/llms.txt > Use this file to discover all available pages before exploring further. [Skip to content](#%5Ftop) # Changelog New updates and improvements at Cloudflare. [ Subscribe to RSS ](https://edgetunnel-b2h.pages.dev/changelog/rss/index.xml) [ View RSS feeds ](https://edgetunnel-b2h.pages.dev/fundamentals/new-features/available-rss-feeds/) Developer platform ![hero image](https://edgetunnel-b2h.pages.dev/_astro/hero.CVYJHPAd_26AMqX.svg) May 28, 2026 1. ### [Use Browser Run Quick Actions directly from Workers](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-28-use-browser-run-quick-actions-directly-from-workers/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) You can now call [Browser Run Quick Actions](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/) directly from a [Cloudflare Worker](https://edgetunnel-b2h.pages.dev/workers/) using the `quickAction()` method on the browser binding. This simplifies how Workers interact with Browser Run by removing the need for API tokens or external HTTP requests. Your Worker communicates with Browser Run directly over Cloudflare's network, resulting in simpler code and lower latency. With the `quickAction()` method you can: * [Capture screenshots](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/screenshot-endpoint/) from URLs or HTML * [Generate PDFs](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/pdf-endpoint/) with custom styling, headers, and footers * [Extract HTML content](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/content-endpoint/) from fully rendered pages * [Convert pages to Markdown](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/markdown-endpoint/) * [Extract structured JSON](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/json-endpoint/) using AI * [Scrape elements](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/scrape-endpoint/) with CSS selectors * [Get all links](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/links-endpoint/) from a page * [Capture snapshots](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/snapshot/) (HTML + screenshot in one request) To get started, add a browser binding to your Wrangler configuration: * [ wrangler.jsonc ](#tab-panel-3409) * [ wrangler.toml ](#tab-panel-3410) **JSONC** ```jsonc { "compatibility_date": "2026-03-24", "browser": { "binding": "BROWSER" } } ``` **TOML** ```toml compatibility_date = "2026-03-24" [browser] binding = "BROWSER" ``` Then call any Quick Action directly from your Worker. For example, to capture a screenshot: * [ JavaScript ](#tab-panel-3413) * [ TypeScript ](#tab-panel-3414) **JavaScript** ```js const screenshot = await env.BROWSER.quickAction("screenshot", { url: "https://www.cloudflare.com/", }); ``` **TypeScript** ```ts const screenshot = await env.BROWSER.quickAction("screenshot", { url: "https://www.cloudflare.com/", }); ``` The `quickAction()` method requires a compatibility date of `2026-03-24` or later. For setup instructions and the full list of available actions, refer to [Browser Run Quick Actions](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/). May 28, 2026 1. ### [Wrangler supports SSH ProxyCommand for Containers](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-28-ssh-proxy-command/) [ Containers ](https://edgetunnel-b2h.pages.dev/containers/) [Wrangler](https://edgetunnel-b2h.pages.dev/workers/wrangler/) supports using `wrangler containers ssh` as an OpenSSH `ProxyCommand` for [Containers](https://edgetunnel-b2h.pages.dev/containers/). This lets your local SSH client connect to a running Container through Wrangler. ```sh ssh -o ProxyCommand="wrangler containers ssh %h" cloudchamber@ ``` When standard input and output are piped, Wrangler forwards data to the SSH server in the Container. You can also pass `--stdio` to force this mode. For more information, refer to the [SSH documentation](https://edgetunnel-b2h.pages.dev/containers/ssh/). May 28, 2026 1. ### [Send emails with named recipient addresses](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-28-named-email-recipients/) [ Email Service ](https://edgetunnel-b2h.pages.dev/email-service/) You can now send emails with display names on recipient addresses in addition to the existing `from` support. Pass an object with `email` and an optional `name` field for `to`, `cc`, `bcc`, `replyTo`, or `from`: * [ JavaScript ](#tab-panel-3427) * [ TypeScript ](#tab-panel-3428) **src/index.js** ```js export default { async fetch(request, env) { const response = await env.EMAIL.send({ from: { email: "support@example.com", name: "Support Team" }, to: { email: "jane@example.com", name: "Jane Doe" }, cc: [ "manager@company.com", { email: "team@company.com", name: "Engineering Team" }, ], subject: "Welcome!", html: "

Thanks for joining!

", text: "Thanks for joining!", }); return Response.json({ messageId: response.messageId }); }, }; ``` **src/index.ts** ```ts export default { async fetch(request, env): Promise { const response = await env.EMAIL.send({ from: { email: "support@example.com", name: "Support Team" }, to: { email: "jane@example.com", name: "Jane Doe" }, cc: [ "manager@company.com", { email: "team@company.com", name: "Engineering Team" }, ], subject: "Welcome!", html: "

Thanks for joining!

", text: "Thanks for joining!", }); return Response.json({ messageId: response.messageId }); }, } satisfies ExportedHandler; ``` Plain strings remain fully supported for backward compatibility, and you can mix strings and named objects in the same array. Refer to the [Workers API](https://edgetunnel-b2h.pages.dev/email-service/api/send-emails/workers-api/) and [REST API](https://edgetunnel-b2h.pages.dev/email-service/api/send-emails/rest-api/) documentation for full request examples. May 28, 2026 1. ### [Pipelines pricing announced](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-11-pipelines-pricing-announced/) [ Pipelines ](https://edgetunnel-b2h.pages.dev/pipelines/) [Cloudflare Pipelines](https://edgetunnel-b2h.pages.dev/pipelines/) is a streaming data platform that ingests events, transforms them with SQL, and writes to [R2](https://edgetunnel-b2h.pages.dev/r2/) as JSON, Parquet, or [Apache Iceberg ↗](https://iceberg.apache.org/) tables. Pipelines now has published pricing based on two usage dimensions: the volume of data processed by SQL transforms and the volume of data delivered to sinks. Ingress into a Pipeline stream is free. **Billing is not yet enabled. We will provide at least 30 days notice before we start charging for Pipelines usage.** Pipelines pricing model is designed to charge per GB based on what you use: * **Streams (ingress)**: Free, regardless of volume. * **SQL transforms**: $0.04 / GB for stateless transforms (filter, reshape, unnest, cast, compute). * **Sinks**: $0.03 / GB for JSON, $0.06 / GB for Parquet or Iceberg output. Workers Free plans include 1 GB / month for each dimension. Workers Paid plans include 50 GB / month. For full pricing details and billing examples, refer to [Pipelines pricing](https://edgetunnel-b2h.pages.dev/pipelines/platform/pricing/). May 28, 2026 1. ### [R2 SQL pricing announced](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-11-r2-sql-pricing-announced/) [ R2 SQL ](https://edgetunnel-b2h.pages.dev/r2-sql/) [R2 SQL](https://edgetunnel-b2h.pages.dev/r2-sql/) is a serverless, distributed query engine that runs SQL against [Apache Iceberg ↗](https://iceberg.apache.org/) tables stored in [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/). R2 SQL now has published pricing based on a single dimension: the volume of compressed data scanned to execute your queries. At $2.50 / TB ($0.0025 / GB), R2 SQL is priced at half the cost of AWS Athena and less than half of Google BigQuery on-demand. Billing is not yet enabled. We will provide at least 30 days notice before we start charging for R2 SQL usage. Data scanned is measured on compressed bytes read from R2 object storage. This matches what you see in your R2 bucket — if a Parquet file is 100 MB on disk, scanning that file bills for 100 MB. Each query has a minimum billing increment of 10 MB. Free plans include 1 GB / month and Paid plans include 10 GB / month. Standard [R2 storage and operations](https://edgetunnel-b2h.pages.dev/r2/pricing/) and [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/platform/pricing/) charges apply separately. For full pricing details and billing examples, refer to [R2 SQL pricing](https://edgetunnel-b2h.pages.dev/r2-sql/platform/pricing/). May 28, 2026 1. ### [R2 Data Catalog pricing announced](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-11-r2-data-catalog-pricing-announced/) [ R2 ](https://edgetunnel-b2h.pages.dev/r2/) [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/) is a managed [Apache Iceberg ↗](https://iceberg.apache.org/) data catalog built directly into R2 buckets, queryable by any Iceberg-compatible engine such as Spark, Snowflake, and DuckDB. R2 Data Catalog now has published pricing for catalog operations and table compaction, in addition to standard [R2 storage and operations](https://edgetunnel-b2h.pages.dev/r2/pricing/). Billing is not yet enabled. We will provide at least 30 days notice before we start charging for R2 Data Catalog usage. Pricing is based on two dimensions: * **Catalog operations**: $9.00 / million operations for metadata requests such as creating tables, reading table metadata, and updating table properties. * **Compaction**: $0.005 / GB processed and $2.00 / million objects processed. These charges only apply when automatic compaction is turned on for a table. Both dimensions include a monthly free tier: 1 million catalog operations, 10 GB of compaction data processed, and 1 million compaction objects processed. For full pricing details and billing examples, refer to [R2 Data Catalog pricing](https://edgetunnel-b2h.pages.dev/r2/data-catalog/platform/pricing/). May 28, 2026 1. ### [R2 Data Catalog gets a dedicated dashboard experience](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-28-r2-data-catalog-dashboard/) [ R2 ](https://edgetunnel-b2h.pages.dev/r2/) [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/) is a managed [Apache Iceberg ↗](https://iceberg.apache.org/) data catalog built directly into your R2 bucket. It exposes a standard Iceberg REST catalog interface so you can connect query engines like [Spark](https://edgetunnel-b2h.pages.dev/r2/data-catalog/config-examples/spark-scala/), [Snowflake](https://edgetunnel-b2h.pages.dev/r2/data-catalog/config-examples/snowflake/), [DuckDB](https://edgetunnel-b2h.pages.dev/r2/data-catalog/config-examples/duckdb/), and [R2 SQL](https://edgetunnel-b2h.pages.dev/r2-sql/) to your data in R2. R2 Data Catalog now has a dedicated section in the Cloudflare dashboard, replacing the previous settings panel embedded in R2 bucket configuration. The new experience includes: ![R2 Data Catalog dashboard overview](https://edgetunnel-b2h.pages.dev/_astro/data-catalog-dashboard.BsKDvUQn_Z1Twgl3.webp) * **Catalog overview** — View all your catalogs in one place with catalog request counts, bucket sizes, and table maintenance status at a glance. * **Guided setup wizard** — Create a catalog in three steps: choose or create an R2 bucket, configure table maintenance (compaction and snapshot expiration), and review. The wizard creates the bucket and generates a service credential automatically. * **Settings management** — A dedicated settings page for each catalog with sections for general configuration, table maintenance, service credentials, and disabling the catalog. You can now enable and configure [snapshot expiration](https://edgetunnel-b2h.pages.dev/r2/data-catalog/table-maintenance/) directly from the dashboard. * **Built-in metrics** — Five charts on each catalog's metrics tab: bytes compacted, files compacted, catalog requests, storage size, and snapshots expired. To get started, go to **R2 Data Catalog** in the Cloudflare dashboard or refer to the [getting started guide](https://edgetunnel-b2h.pages.dev/r2/data-catalog/get-started/) and [manage catalogs documentation](https://edgetunnel-b2h.pages.dev/r2/data-catalog/manage-catalogs/). May 28, 2026 1. ### [Record specific participant audio tracks in RealtimeKit](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-28-realtimekit-track-recording/) [ Realtime ](https://edgetunnel-b2h.pages.dev/realtime/) You can now record specific participant audio tracks in RealtimeKit with [track recording](https://edgetunnel-b2h.pages.dev/realtime/realtimekit/recording-guide/track-recording/). Track recording creates separate WebM files for each participant instead of a single composite recording, which is useful for post-processing, transcription, and regulated or content-sensitive workflows. To record specific participants, pass `user_ids` when starting a track recording: ```bash curl --request POST \ --url https://api.cloudflare.com/client/v4/accounts//realtime/kit//recordings/track \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data '{ "meeting_id": "97440c6a-140b-40a9-9499-b23fd7a3868a", "user_ids": ["user-123", "user-456"] }' ``` To pass `user_ids` for selective track recording, use the following minimum SDK versions: * Web Core: `@cloudflare/realtimekit` version `1.4.0` or later * Web UI Kit: `@cloudflare/realtimekit-ui`, `@cloudflare/realtimekit-react-ui`, or `@cloudflare/realtimekit-angular-ui` version `1.1.2` or later * Android Core or iOS Core: version `2.0.0` or later * Android UI Kit or iOS UI Kit: version `1.1.0` or later [RealtimeKit](https://edgetunnel-b2h.pages.dev/realtime/realtimekit/) provides SDKs and UI components so that you can build your own meeting experience on Cloudflare's [global WebRTC infrastructure](https://edgetunnel-b2h.pages.dev/realtime/#realtime-sfu). Teams today build products ranging from telehealth to education on RealtimeKit for global audiences. You can get started today with our [Quickstart](https://edgetunnel-b2h.pages.dev/realtime/realtimekit/quickstart/) or take a look at our [Cloudflare Meet repo ↗](https://github.com/cloudflare/meet) as a reference. May 27, 2026 1. ### [Transformation flows in Images](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-27-transformation-flows/) [ Cloudflare Images ](https://edgetunnel-b2h.pages.dev/images/) ![Custom flow configuration panel](https://edgetunnel-b2h.pages.dev/_astro/custom-flow.DeAGR8BY_iGLSK.webp) Flows are automated rules that pair conditions (such as file extension, URL path, or query parameter) with parameters. Set up a flow to automatically apply image optimization to matching requests on your zone without writing code or changing URLs. There are two modes for transformation flows: * **[Provider flows](https://edgetunnel-b2h.pages.dev/images/optimization/transformations/flows/#set-up-a-provider-flow)** — Migrate from another image optimization service. Your existing URLs continue to work while Cloudflare rewrites provider-specific parameters to their Cloudflare equivalents. Currently, Cloudflare supports provider flows for Fastly Image Optimizer. * **[Custom flows](https://edgetunnel-b2h.pages.dev/images/optimization/transformations/flows/#set-up-a-custom-flow)** — Define your own conditions and actions for use cases like automatic format conversion, [responsive sizing](https://edgetunnel-b2h.pages.dev/images/optimization/make-responsive-images/#using-widthauto) with `width=auto`, or directory-based optimization. To get started, go to **Images** \> **Transformations** \> **Automation** in the [Cloudflare dashboard ↗](https://dash.cloudflare.com/?to=/:account/images/transformations). Learn more about [transformation flows](https://edgetunnel-b2h.pages.dev/images/optimization/transformations/flows/). May 27, 2026 1. ### [Cloudflare Tunnel now runs connectivity pre-checks at startup](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-27-cloudflared-connectivity-prechecks/) [ Cloudflare Tunnel ](https://edgetunnel-b2h.pages.dev/tunnel/)[ Cloudflare Tunnel for SASE ](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-tunnel/) Starting with [cloudflared version 2026.5.2 ↗](https://github.com/cloudflare/cloudflared/releases), [Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/tunnel/) automates the entire [connectivity pre-checks workflow](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-tunnel/troubleshoot-tunnels/connectivity-prechecks/) directly inside the binary. Previously, customers had to install `dig` and `netcat` and run those commands by hand to verify their environment. Now `cloudflared` does it natively at startup — and surfaces actionable remediation when something is blocked. ![cloudflared connectivity pre-checks output](https://edgetunnel-b2h.pages.dev/_astro/cloudflared-connectivity-prechecks.DRwN6tGe_c1XGu.webp) On every `cloudflared tunnel run` (and `cloudflared tunnel diag`), the binary now natively checks: * **DNS resolution** — `region1.v2.argotunnel.com` and `region2.v2.argotunnel.com` resolve to valid Cloudflare IPs. * **Transport connectivity** — outbound `UDP (QUIC)` and `TCP (HTTP/2)` on port `7844`. * **Management API** — outbound `TCP/443` to `api.cloudflare.com` for software updates. Results are printed in a scannable CLI table with three states: * ✅ **Pass** — the check succeeded. * ⚠️ **Warn** — a non-blocking issue, for example the Management API is unreachable so automatic updates will not work, but the tunnel will still come up. * ❌ **Fail** — a blocking issue, with a specific remediation hint (for example, `Allow outbound UDP on port 7844`). If DNS is unresolvable, or **both** UDP and TCP fail on port 7844, `cloudflared` exits early with the failure rather than looping on opaque `failed to dial` errors. Pre-checks now run automatically on every start, which also catches regressions like overnight firewall policy changes — no need to remember to rerun the troubleshooting guide. To get the new behavior, upgrade `cloudflared` to version `2026.5.2` or later. For more details, refer to the [Connectivity pre-checks documentation](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-tunnel/troubleshoot-tunnels/connectivity-prechecks/). May 26, 2026 1. ### [Flagship now in public beta](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-26-public-beta/) [ Flagship ](https://edgetunnel-b2h.pages.dev/flagship/) **[Flagship](https://edgetunnel-b2h.pages.dev/flagship/)** is now in public beta. Evaluate feature flags directly from Cloudflare Workers with no outbound HTTP calls, using globally distributed flag configuration backed by Workers KV and Durable Objects. Flagship supports typed flag values, targeting rules, percentage rollouts, audit history, and OpenFeature-compatible SDKs. Evaluate a flag from a Worker in a few lines of code: * [ JavaScript ](#tab-panel-3421) * [ TypeScript ](#tab-panel-3422) **src/index.js** ```js export default { async fetch(request, env) { const showNewCheckout = await env.FLAGS.getBooleanValue( "new-checkout", false, ); return new Response(showNewCheckout ? "New checkout" : "Standard checkout"); }, }; ``` **src/index.ts** ```ts export default { async fetch(request: Request, env: Env): Promise { const showNewCheckout = await env.FLAGS.getBooleanValue("new-checkout", false); return new Response( showNewCheckout ? "New checkout" : "Standard checkout", ); }, } satisfies ExportedHandler; ``` Start creating flags from the Cloudflare dashboard today. Refer to the [Flagship documentation](https://edgetunnel-b2h.pages.dev/flagship/get-started/) to get started. May 21, 2026 1. ### [Call any AI model through AI Gateway's new REST API](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-21-rest-api/) [ AI Gateway ](https://edgetunnel-b2h.pages.dev/ai-gateway/) AI Gateway now uses the AI REST API on `api.cloudflare.com`. You can call any model — whether from OpenAI, Anthropic, Google, or hosted on Workers AI — through one unified API, using the same endpoints and authentication regardless of provider. Four endpoints are available: * `POST /ai/run` — universal endpoint for all models and modalities * `POST /ai/v1/chat/completions` — OpenAI SDK compatible * `POST /ai/v1/responses` — OpenAI Responses API compatible * `POST /ai/v1/messages` — Anthropic SDK compatible ```bash curl -X POST "https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions" \ --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \ --header "Content-Type: application/json" \ --data '{ "model": "openai/gpt-5.5", "messages": [{"role": "user", "content": "What is Cloudflare?"}] }' ``` All AI Gateway features — logging, caching, rate limiting, and guardrails — are applied automatically. Third-party models are billed through [Unified Billing](https://edgetunnel-b2h.pages.dev/ai-gateway/features/unified-billing/), so you do not need to manage separate provider API keys. Third-party model requests are routed through your account's default gateway, which is created automatically on first use. To route requests through a specific gateway, add the `cf-aig-gateway-id` header. If you are already calling Workers AI models through the existing REST API, that path (`/ai/run/@cf/{model}`) continues to work. To call Workers AI models through AI Gateway, use the `@cf/` model prefix (for example, `@cf/moonshotai/kimi-k2.6`) and include the `cf-aig-gateway-id` header to specify which gateway to route through. For more details and examples, refer to the [REST API documentation](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/rest-api/). May 21, 2026 1. ### [Granular permissions for Cloudflare Tunnel and Cloudflare Mesh](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-21-tunnel-mesh-granular-permissions/) [ Cloudflare Fundamentals ](https://edgetunnel-b2h.pages.dev/fundamentals/)[ Cloudflare One ](https://edgetunnel-b2h.pages.dev/cloudflare-one/)[ Cloudflare Tunnel for SASE ](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-tunnel/)[ Cloudflare Tunnel ](https://edgetunnel-b2h.pages.dev/tunnel/)[ Cloudflare Mesh ](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-mesh/) You can now scope Cloudflare permissions to individual [Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/tunnel/) instances and [Cloudflare Mesh](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-mesh/) nodes. Administrators can delegate access to specific Tunnels or Mesh nodes without granting account-wide control over private networking. #### What is new When you [add a member](https://edgetunnel-b2h.pages.dev/fundamentals/manage-members/manage/) or create a [permission policy](https://edgetunnel-b2h.pages.dev/fundamentals/manage-members/policies/), the resource picker now lists [Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/tunnel/) instances and [Cloudflare Mesh](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-mesh/) nodes as scopable resource types. You can: * Grant a read-only role on a single Cloudflare Tunnel instance to a support operator for log streaming and diagnostics — without exposing other Tunnels or destructive actions. * Grant a write role on a specific Cloudflare Mesh node to an application team — without giving them access to the rest of your private network. * Scope a single policy to one or many Tunnels and Mesh nodes at once. #### How it works Granular permissions are a parallel layer to existing account-level roles — they do not replace them. * **Existing account-level roles continue to work.** A member with `Cloudflare Access` or `Cloudflare Zero Trust` retains write access to every Tunnel and Mesh node in the account. This ensures backward compatibility for existing automation and tokens. * **Granular permissions are additive.** For any API request on a specific Tunnel or Mesh node, access is granted if the principal has **either** the account-level role **or** a granular permission for that resource. * **Resource enumeration is authorization-aware.** Listing endpoints (`GET /accounts/{id}/cfd_tunnel`, `GET /accounts/{id}/warp_connector`) return only the resources the principal has at least read access to. #### Get started * Configure [granular permissions for Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/tunnel/advanced/granular-permissions/). * Configure [granular permissions for Cloudflare Tunnel and Cloudflare Mesh in Cloudflare One](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/granular-permissions/). * Review the [resource-scoped roles](https://edgetunnel-b2h.pages.dev/fundamentals/manage-members/roles/#resource-scoped-roles) on the Cloudflare role reference. May 21, 2026 1. ### [Reach Cloudflare WAN destinations from Workers VPC](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-21-vpc-networks-cloudflare-wan/) [ Workers VPC ](https://edgetunnel-b2h.pages.dev/workers-vpc/) You can now use [VPC Network](https://edgetunnel-b2h.pages.dev/workers-vpc/configuration/vpc-networks/) bindings with `network_id: "cf1:network"` to reach your full private network from Workers, including: * [Cloudflare Mesh](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-mesh/) nodes and client devices * Subnet routes and hostname routes announced through [Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/cloudflare-one/networks/connectors/cloudflare-tunnel/) or Cloudflare Mesh * Destinations connected through [Cloudflare WAN](https://edgetunnel-b2h.pages.dev/cloudflare-wan/) on-ramps — GRE, IPsec, and CNI This means a single VPC Network binding can route Worker requests to private services regardless of how those services are connected to Cloudflare: through a Cloudflare Tunnel from a cloud VPC, a Mesh node on a private subnet, or a Cloudflare WAN on-ramp from your data center or branch site. * [ wrangler.jsonc ](#tab-panel-3411) * [ wrangler.toml ](#tab-panel-3412) **JSONC** ```jsonc { "vpc_networks": [ { "binding": "PRIVATE_NETWORK", "network_id": "cf1:network", "remote": true, }, ], } ``` **TOML** ```toml [[vpc_networks]] binding = "PRIVATE_NETWORK" network_id = "cf1:network" remote = true ``` At runtime, the URL you pass to `fetch()` determines the destination: **JavaScript** ```js // Reach a service behind a Cloudflare WAN IPsec on-ramp const response = await env.PRIVATE_NETWORK.fetch("http://10.50.0.100:8080/api"); ``` Note For destinations behind Cloudflare WAN on-ramps (GRE, IPsec, or CNI), your network must route the [Cloudflare source IP range](https://edgetunnel-b2h.pages.dev/cloudflare-wan/configuration/how-to/configure-cloudflare-source-ips/) back through the on-ramp so reply traffic returns to Cloudflare. Without this route, stateful flows will fail. This is part of standard Cloudflare WAN onboarding. For configuration options, refer to [VPC Networks](https://edgetunnel-b2h.pages.dev/workers-vpc/configuration/vpc-networks/). May 19, 2026 1. ### [Event subscriptions for Artifacts lifecycle events](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-19-event-subscriptions/) [ Artifacts ](https://edgetunnel-b2h.pages.dev/artifacts/)[ Queues ](https://edgetunnel-b2h.pages.dev/queues/) You can now receive [event notifications](https://edgetunnel-b2h.pages.dev/queues/event-subscriptions/) for [Artifacts](https://edgetunnel-b2h.pages.dev/artifacts/) repository changes and consume them from a Worker to build commit-driven automation. This allows you to: * Run custom workflows when a repository is created or imported * Kick off a build and deploy a change when an agent pushes to a repo * Trigger a review agent on every push Available events include: * **Account-level events** (`artifacts` source) — `repo.created`, `repo.deleted`, `repo.forked`, `repo.imported` * **Repository-level events** (`artifacts.repo` source) — `pushed`, `cloned`, `fetched` To learn more, refer to [Artifacts documentation](https://edgetunnel-b2h.pages.dev/artifacts/guides/event-subscriptions/). May 18, 2026 1. ### [Manage Artifacts namespaces and repos with Wrangler CLI](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-18-wrangler-support/) [ Artifacts ](https://edgetunnel-b2h.pages.dev/artifacts/) You can now manage [Artifacts](https://edgetunnel-b2h.pages.dev/artifacts/) namespaces, repos, and repo-scoped tokens directly from Wrangler CLI. Available commands: * `wrangler artifacts namespaces list` — List Artifacts namespaces in your account. * `wrangler artifacts namespaces get` — Get metadata for a namespace. * `wrangler artifacts repos create` — Create a repo in a namespace. * `wrangler artifacts repos list` — List repos in a namespace. * `wrangler artifacts repos get` — Get metadata for a repo. * `wrangler artifacts repos delete` — Delete a repo. * `wrangler artifacts repos issue-token` — Issue a repo-scoped token for Git access. To get started, refer to the [Wrangler Artifacts commands documentation](https://edgetunnel-b2h.pages.dev/workers/wrangler/commands/artifacts/). May 18, 2026 1. ### [Share local dev servers through Cloudflare Tunnel in Wrangler and Vite](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-18-local-dev-tunnels/) [ Workers ](https://edgetunnel-b2h.pages.dev/workers/) You can now share local dev sessions through [Cloudflare Tunnel](https://edgetunnel-b2h.pages.dev/tunnel/) and get a public URL when using either [Wrangler](https://edgetunnel-b2h.pages.dev/workers/wrangler/) or the [Cloudflare Vite plugin](https://edgetunnel-b2h.pages.dev/workers/vite-plugin/). This is useful when you need to share a preview, test a webhook, or access your app from another device. ![Vite local dev tunnel demo](https://edgetunnel-b2h.pages.dev/_astro/vite-local-dev-tunnel.CW4xpgIR_ZmyQ8a.webp) This lets you either: * start a temporary [Quick tunnel](https://edgetunnel-b2h.pages.dev/tunnel/setup/#quick-tunnels-development) with a random `*.trycloudflare.com` hostname, or * use an existing [named tunnel](https://edgetunnel-b2h.pages.dev/tunnel/setup/#create-a-tunnel) for a stable hostname and to restrict access with [Cloudflare Access](https://edgetunnel-b2h.pages.dev/cloudflare-one/access-controls/). To start a tunnel, press `t` in Wrangler or `t + Enter` in Vite while your dev server is running. For details on setting up a named tunnel, refer to [Share a local dev server](https://edgetunnel-b2h.pages.dev/workers/local-development/local-dev-tunnels/). May 15, 2026 1. ### [Hyperdrive exposes database connection pool size metrics](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-15-hyperdrive-pool-size-metrics/) [ Hyperdrive ](https://edgetunnel-b2h.pages.dev/hyperdrive/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) You can now view the size of your Hyperdrive database connection pools, giving you the ability to self-diagnose connection issues. Using the Cloudflare dashboard or the `hyperdrivePoolSizesAdaptiveGroups` dataset in the [GraphQL Analytics API](https://edgetunnel-b2h.pages.dev/analytics/graphql-api/getting-started/), you can see `waitingClients`, `currentPoolSize`, `availablePoolSlots`, and `maxPoolSize` for each of your configurations. A new **Pool connections** chart has been added to the **Metrics** tab of each Hyperdrive configuration in the [Cloudflare dashboard ↗](https://dash.cloudflare.com). You can use the location selector to drill down into specific locations hosting your connection pool by airport code. ![Hyperdrive pool size metrics chart](https://edgetunnel-b2h.pages.dev/_astro/hyperdrive-pool-size-metrics-chart.DZxLTFgB_3zcIK.webp) The chart shows: * **Waiting clients**: Client requests waiting for an available connection. * **Open connections**: Active connections to your database. * **Pool size maximum**: Your configured origin connection limit. Connection contention appears as a spike in waiting clients, or when open connections consistently approach the pool size maximum. If your open connections regularly approach this limit, consider contacting Cloudflare to [increase your Hyperdrive connection limit](https://edgetunnel-b2h.pages.dev/hyperdrive/platform/limits/#request-a-limit-increase). #### Pool size metrics The `hyperdrivePoolSizesAdaptiveGroups` dataset in the [GraphQL Analytics API](https://edgetunnel-b2h.pages.dev/analytics/graphql-api/getting-started/) exposes the following key connection pool metrics for each Hyperdrive configuration: Under `avg`: * **`currentPoolSize`** — Average number of connections currently open in the pool. * **`availablePoolSlots`** — Average number of pool connections available for checkout. * **`waitingClients`** — Average number of clients waiting for a connection from the pool. Under `max`: * **`maxPoolSize`** — Configured maximum size of the connection pool. * **`currentPoolSize`** — Peak number of connections open in the pool. * **`waitingClients`** — Peak number of clients waiting for a connection from the pool. For more information, refer to [Metrics and analytics](https://edgetunnel-b2h.pages.dev/hyperdrive/observability/metrics/) and [Connection pooling](https://edgetunnel-b2h.pages.dev/hyperdrive/concepts/connection-pooling/). May 15, 2026 1. ### [R2 SQL now supports JOINs, subqueries, and multi-table queries](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-14-joins-subqueries-multi-table-queries/) [ R2 SQL ](https://edgetunnel-b2h.pages.dev/r2-sql/) [R2 SQL](https://edgetunnel-b2h.pages.dev/r2-sql/) is Cloudflare's serverless, distributed SQL engine for querying [Apache Iceberg ↗](https://iceberg.apache.org/) tables stored in [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/). R2 SQL runs directly on Cloudflare's global network with no infrastructure to manage, so you can analyze data in R2 without exporting it to an external warehouse. R2 SQL now supports joining multiple Iceberg tables in a single query. You can combine tables with JOINs, filter with subqueries, and define multi-table CTEs to build complex analytical queries. #### New capabilities * **JOINs** — `INNER JOIN`, `LEFT JOIN`, `RIGHT JOIN`, `FULL OUTER JOIN`, `CROSS JOIN`, and implicit joins (comma-separated `FROM` with conditions in `WHERE`) * **Subqueries** — `IN` / `NOT IN`, `EXISTS` / `NOT EXISTS`, scalar subqueries in `SELECT` / `WHERE` / `HAVING`, and derived tables (subqueries in `FROM`) * **Multi-table CTEs** — `WITH` clauses can reference different tables and include JOINs * **Self-joins** — join a table with itself using different aliases * **Multi-way joins** — join three or more tables in a single query #### Examples #### Two-table JOIN with aggregation ```sql SELECT z.domain, z.plan, COUNT(*) AS request_count FROM my_namespace.zones z INNER JOIN my_namespace.http_requests h ON z.zone_id = h.zone_id WHERE z.plan = 'enterprise' GROUP BY z.domain, z.plan ORDER BY request_count DESC LIMIT 20 ``` #### `EXISTS` subquery ```sql SELECT z.domain, z.plan FROM my_namespace.zones z WHERE EXISTS ( SELECT 1 FROM my_namespace.firewall_events f WHERE f.zone_id = z.zone_id AND f.action = 'block' ) ORDER BY z.domain LIMIT 20 ``` #### Multi-table CTE with JOIN ```sql WITH top_zones AS ( SELECT zone_id, COUNT(*) AS req_count FROM my_namespace.http_requests GROUP BY zone_id ORDER BY req_count DESC LIMIT 50 ), zone_threats AS ( SELECT zone_id, COUNT(*) AS threat_count FROM my_namespace.firewall_events WHERE risk_score > 0.5 GROUP BY zone_id ) SELECT tz.zone_id, tz.req_count, COALESCE(zt.threat_count, 0) AS threat_count FROM top_zones tz LEFT JOIN zone_threats zt ON tz.zone_id = zt.zone_id ORDER BY tz.req_count DESC LIMIT 20 ``` For the full syntax reference, refer to the [SQL reference](https://edgetunnel-b2h.pages.dev/r2-sql/sql-reference/). For performance guidance with joins, refer to [Limitations and best practices](https://edgetunnel-b2h.pages.dev/r2-sql/reference/limitations-best-practices/). May 14, 2026 1. ### [New Domains tab in the Workers dashboard](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-14-domains-tab/) [ Workers ](https://edgetunnel-b2h.pages.dev/workers/) In your Worker's dashboard, there is now a dedicated **Domains** tab where you can purchase a new domain through Cloudflare Registrar and have it automatically connected, add an [existing domain](https://edgetunnel-b2h.pages.dev/workers/configuration/routing/custom-domains/), and manage all of your Worker's routing in one place. ![The new Domains tab in the Workers dashboard](https://edgetunnel-b2h.pages.dev/_astro/domains-tab.Cey2Oyr-_B4kIf.webp) You can also enable or disable your [workers.dev subdomain](https://edgetunnel-b2h.pages.dev/workers/configuration/routing/workers-dev/) and [Preview URLs](https://edgetunnel-b2h.pages.dev/workers/versions-and-deployments/preview-urls/), put them behind [Cloudflare Access](https://edgetunnel-b2h.pages.dev/cloudflare-one/access-controls/) to require sign-in, and jump directly to [analytics](https://edgetunnel-b2h.pages.dev/analytics/) or domain overview for any connected domain. To get started, go to **Workers & Pages**, select a Worker, and open the **Domains** tab. [ Go to **Workers & Pages** ](https://dash.cloudflare.com/?to=/:account/workers-and-pages) May 13, 2026 1. ### [Agents SDK v0.12.4: chat recovery, routing retries, durable Think submissions, and Voice connection control](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-13-agents-sdk-v0124/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) The latest release of the [Agents SDK ↗](https://github.com/cloudflare/agents) brings more reliable chat recovery, fixes Agent state synchronization during reconnects, adds durable submissions for Think, exposes routing retry configuration, and adds connection control for Voice agents. #### Chat recovery improvements `@cloudflare/ai-chat` now keeps server turns running when a browser or client stream is interrupted. This is useful for long-running AI responses where users refresh the page, close a tab, or temporarily lose connection. Calling `stop()` still cancels the server turn. Set `cancelOnClientAbort: true` if browser or client aborts should also cancel the server turn: * [ JavaScript ](#tab-panel-3419) * [ TypeScript ](#tab-panel-3420) **JavaScript** ```js const chat = useAgentChat({ agent: "assistant", name: "user-123", cancelOnClientAbort: true, }); ``` **TypeScript** ```ts const chat = useAgentChat({ agent: "assistant", name: "user-123", cancelOnClientAbort: true, }); ``` Notable bug fixes: * Chat stream resume negotiation no longer throws when replay races with a closed WebSocket connection. * Recovered chat continuations no longer leave `useAgentChat` stuck in a streaming state when the original socket disconnects before a terminal response. * Approval auto-continuation preserves reasoning parts and persists continuation reasoning in the final message. * `isServerStreaming` now resets correctly when a resumed stream moves from the fallback observer path to a transport-owned stream. #### Agent state and routing fixes `agents@0.12.4` prevents duplicate initial state frames during WebSocket connection setup. This avoids stale initial state messages overwriting state updates already sent by the client. Agent recovery is also more reliable when tool calls span a Durable Object restart. Recovery now defers user finish hooks until after agent startup and isolates hook failures, so one failed hook does not block other recovered runs from finalizing. `getAgentByName()` now supports `routingRetry` for transient Durable Object routing failures: * [ JavaScript ](#tab-panel-3423) * [ TypeScript ](#tab-panel-3424) **JavaScript** ```js import { getAgentByName } from "agents"; const agent = await getAgentByName(env.AssistantAgent, "user-123", { routingRetry: { maxAttempts: 3, }, }); ``` **TypeScript** ```ts import { getAgentByName } from "agents"; const agent = await getAgentByName(env.AssistantAgent, "user-123", { routingRetry: { maxAttempts: 3, }, }); ``` #### Durable Think submissions `@cloudflare/think` now supports durable programmatic submissions. `submitMessages()` provides durable acceptance, idempotent retries, status inspection, cancellation, and cleanup for server-driven turns that should continue after the caller returns. `Think.chat()` RPC turns now run inside chat recovery fibers and persist their stream chunks. Interrupted sub-agent turns can recover partial output instead of starting over. `ChatOptions.tools` has been removed from the TypeScript API. Define durable tools on the child agent or use agent tools for orchestration. Runtime `options.tools` values passed by legacy callers are ignored with a warning. #### Think message pruning behavior change `@cloudflare/think` no longer applies `pruneMessages({ toolCalls: "before-last-2-messages" })` to model context by default. The previous default could strip client-side tool results from longer multi-turn flows. `truncateOlderMessages` still runs as before, so context cost remains bounded. Subclasses that relied on the old aggressive pruning can opt back in from `beforeTurn`: * [ JavaScript ](#tab-panel-3429) * [ TypeScript ](#tab-panel-3430) **JavaScript** ```js import { Think } from "@cloudflare/think"; import { pruneMessages } from "ai"; export class MyAgent extends Think { beforeTurn(ctx) { return { messages: pruneMessages({ messages: ctx.messages, toolCalls: "before-last-2-messages", }), }; } } ``` **TypeScript** ```ts import { Think } from "@cloudflare/think"; import { pruneMessages } from "ai"; export class MyAgent extends Think { beforeTurn(ctx) { return { messages: pruneMessages({ messages: ctx.messages, toolCalls: "before-last-2-messages", }), }; } } ``` #### Voice agent connection control `@cloudflare/voice` adds an `enabled` option to `useVoiceAgent`. React apps can now delay creating and connecting a `VoiceClient` until prerequisites such as capability tokens are ready. * [ JavaScript ](#tab-panel-3425) * [ TypeScript ](#tab-panel-3426) **JavaScript** ```js const voice = useVoiceAgent({ agent: "MyVoiceAgent", enabled: Boolean(token), }); ``` **TypeScript** ```ts const voice = useVoiceAgent({ agent: "MyVoiceAgent", enabled: Boolean(token), }); ``` This release also fixes Workers AI speech-to-text session edge cases and `withVoice` text streaming from AI SDK `textStream` responses. #### Other improvements * **Streamable HTTP routing** — Server-to-client requests now route through the originating POST stream when no standalone SSE stream is available. * **Structured tool output** — Tool output shapes are preserved when truncating older messages or oversized persisted rows. * **Non-chat Think tool steps** — Think agent-tool children can complete without emitting assistant text and can return structured output through `getAgentToolOutput`. * **Sub-agent schedules** — Stale sub-agent schedule rows are pruned when their owning facet registry entry no longer exists. * **`@cloudflare/codemode`** — Adds a browser-safe export with an iframe sandbox executor and resolves OpenAPI specs inside the sandbox to avoid Worker Loader RPC size limits. #### Upgrade To update to the latest version: ```sh npm i agents@latest @cloudflare/ai-chat@latest @cloudflare/think@latest @cloudflare/voice@latest ``` Refer to the [Agents API reference](https://edgetunnel-b2h.pages.dev/agents/runtime/) and [Chat agents documentation](https://edgetunnel-b2h.pages.dev/agents/communication-channels/chat/chat-agents/) for more information. May 13, 2026 1. ### [/cdn-cgi/rum endpoint now returns 405 for non-POST requests](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-13-rum-405-method-not-allowed/) [ Cloudflare Web Analytics ](https://edgetunnel-b2h.pages.dev/web-analytics/) The `/cdn-cgi/rum` beacon endpoint now returns `405 Method Not Allowed` for non-POST requests instead of `404 Not Found`. The response includes an `Allow: POST, OPTIONS` header per [RFC 9110 §15.5.6 ↗](https://www.rfc-editor.org/rfc/rfc9110#section-15.5.6). Previously, sending a `GET` or other non-POST request to this endpoint returned a `404`, which was misleading because it suggested the endpoint did not exist. The new `405` response clearly indicates that the endpoint exists but only accepts `POST` requests. The Web Analytics beacon (`beacon.min.js`) already uses `POST` for all metric submissions, so this change does not affect normal beacon operation. `OPTIONS` requests for CORS preflight continue to work as before. For more information, refer to the [Web Analytics FAQ](https://edgetunnel-b2h.pages.dev/web-analytics/faq/#why-am-i-getting-a-405-method-not-allowed-error-from-cdn-cgirum). May 12, 2026 1. ### [SSH through Wrangler is now enabled by default for Containers](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-12-ssh-enabled-by-default/) [ Containers ](https://edgetunnel-b2h.pages.dev/containers/) SSH through Wrangler is now enabled by default for [Containers](https://edgetunnel-b2h.pages.dev/containers/). Previously, you had to set `ssh.enabled` to `true` in your Container configuration before you could connect. This change does not expose any publicly accessible ports on your Container. The SSH service is reachable only through [wrangler containers ssh](https://edgetunnel-b2h.pages.dev/workers/wrangler/commands/containers/#containers-ssh), which authenticates against your Cloudflare account. You also need to add an `ssh-ed25519` public key to `authorized_keys` before anyone can connect, so enabling SSH alone does not grant access. To connect, add a public key to your Container configuration and run `wrangler containers ssh `: * [ wrangler.jsonc ](#tab-panel-3417) * [ wrangler.toml ](#tab-panel-3418) **JSONC** ```jsonc { "containers": [ { "authorized_keys": [ { "name": "", "public_key": "", }, ], }, ], } ``` **TOML** ```toml [[containers]] [[containers.authorized_keys]] name = "" public_key = "" ``` To disable SSH, set `ssh.enabled` to `false` in your Container configuration: * [ wrangler.jsonc ](#tab-panel-3415) * [ wrangler.toml ](#tab-panel-3416) **JSONC** ```jsonc { "containers": [ { "ssh": { "enabled": false, }, }, ], } ``` **TOML** ```toml [[containers]] [containers.ssh] enabled = false ``` For more information, refer to the [SSH documentation](https://edgetunnel-b2h.pages.dev/containers/ssh/). May 12, 2026 1. ### [R2 Data Catalog now exposes metrics via the GraphQL Analytics API](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-12-r2-data-catalog-graphql-analytics/) [ R2 ](https://edgetunnel-b2h.pages.dev/r2/) [R2 Data Catalog](https://edgetunnel-b2h.pages.dev/r2/data-catalog/) is a managed Apache Iceberg data catalog built directly into your R2 bucket that allows you to connect query engines like [R2 SQL](https://edgetunnel-b2h.pages.dev/r2-sql/), Spark, Snowflake, and DuckDB to your data in R2. You can now query analytics for your R2 Data Catalog warehouses via Cloudflare's [GraphQL Analytics API](https://edgetunnel-b2h.pages.dev/analytics/graphql-api/). Two new datasets are available: * **`r2CatalogDataOperationsAdaptiveGroups`** tracks Iceberg REST API requests made to your catalog, including operation type, request duration, HTTP status, and request body bytes. Use this to monitor request volume and latency across warehouses, namespaces, and tables. * **`r2CatalogTableMaintenanceAdaptiveGroups`** tracks table maintenance jobs such as compaction and snapshot expiration. Use this to monitor job success rates, files processed, bytes read and written, and job duration. Both datasets support filtering by warehouse name, namespace, table name, and time range. They also include percentile aggregations for duration metrics. For detailed schema information and example queries, refer to the [R2 Data Catalog metrics and analytics documentation](https://edgetunnel-b2h.pages.dev/r2/data-catalog/observability/metrics/). May 08, 2026 1. ### [Planned model deprecations on Workers AI](https://edgetunnel-b2h.pages.dev/changelog/post/2026-05-08-planned-model-deprecations/) [ Workers AI ](https://edgetunnel-b2h.pages.dev/workers-ai/) We are refreshing the Workers AI model catalog to make room for newer releases. Please update your apps to remove references to the models listed below before the deprecation date. #### Recommended replacements * [@cf/zai-org/glm-4.7-flash](https://edgetunnel-b2h.pages.dev/workers-ai/models/glm-4.7-flash/) — fast multilingual model with multi-turn tool calling and coding capabilities. * [@cf/google/gemma-4-26b-a4b-it](https://edgetunnel-b2h.pages.dev/workers-ai/models/gemma-4-26b-a4b-it/) — efficient open model with vision and tool calling. * [@cf/moonshotai/kimi-k2.6](https://edgetunnel-b2h.pages.dev/workers-ai/models/kimi-k2.6/) — capable tool-calling and vision model for agentic workloads and coding. For pricing, refer to the [Workers AI pricing page](https://edgetunnel-b2h.pages.dev/workers-ai/platform/pricing/). #### Kimi K2.5 We originally stated Kimi K2.5 would be deprecated on May 10, 2026, however we have extended the deprecation date to May 30, 2026\. Requests will be automatically aliased to Kimi K2.6 on May 30, 2026, which has a higher price. Please review the [@cf/moonshotai/kimi-k2.6](https://edgetunnel-b2h.pages.dev/workers-ai/models/kimi-k2.6/) pricing and model capabilities prior to May 30, 2026 to ensure that the model suits your needs. #### Models deprecated on May 30, 2026 * `@cf/moonshotai/kimi-k2.5` \--> `@cf/moonshotai/kimi-k2.6` * `@hf/meta-llama/meta-llama-3-8b-instruct` * `@cf/meta/llama-3-8b-instruct` * `@cf/meta/llama-3-8b-instruct-awq` * `@cf/meta/llama-3.1-8b-instruct` * `@cf/meta/llama-3.1-8b-instruct-awq` * `@cf/meta/llama-3.1-70b-instruct` * `@cf/meta/llama-2-7b-chat-int8` * `@cf/meta/llama-2-7b-chat-fp16` * `@cf/mistral/mistral-7b-instruct-v0.1` * `@hf/mistral/mistral-7b-instruct-v0.2` * `@hf/google/gemma-7b-it` * `@cf/google/gemma-3-12b-it` * `@hf/nousresearch/hermes-2-pro-mistral-7b` * `@cf/microsoft/phi-2` * `@cf/defog/sqlcoder-7b-2` * `@cf/unum/uform-gen2-qwen-500m` * `@cf/facebook/bart-large-cnn` #### Variants that remain active The `-fast` and `-lora` variants of models will remain active, including: * `@cf/meta/llama-3.3-70b-instruct-fp8-fast` * `@cf/meta/llama-3.1-8b-instruct-fast` * `@cf/google/gemma-7b-it-lora` * `@cf/google/gemma-2b-it-lora` * `@cf/mistral/mistral-7b-instruct-v0.2-lora` * `@cf/meta-llama/llama-2-7b-chat-hf-lora` LoRA models may be deprecated in the future. We will be adding more LoRA capabilities to the catalog, and will communicate when new LoRA models come online to give users time to train new LoRAs before we deprecate old ones. For the full list of available models, refer to the [Workers AI model catalog](https://edgetunnel-b2h.pages.dev/workers-ai/models/). ```json {"@context":"https://schema.org","@type":"BlogPosting","@id":"https://edgetunnel-b2h.pages.dev/changelog/product-group/developer-platform/4/#page","headline":"Developer platform Changelog | Cloudflare Docs","url":"https://edgetunnel-b2h.pages.dev/changelog/product-group/developer-platform/4/","inLanguage":"en","image":"https://edgetunnel-b2h.pages.dev/cf-twitter-card.png","publisher":{"@type":"Organization","name":"Cloudflare","url":"https://www.cloudflare.com/"},"isPartOf":{"@type":"WebSite","@id":"https://edgetunnel-b2h.pages.dev/#website","name":"Cloudflare Docs","url":"https://edgetunnel-b2h.pages.dev/"}} ```