--- title: AI 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/) AI ![hero image](https://edgetunnel-b2h.pages.dev/_astro/hero.CVYJHPAd_26AMqX.svg) Aug 05, 2025 1. ### [Cloudflare Sandbox SDK adds streaming, code interpreter, Git support, process control and more](https://edgetunnel-b2h.pages.dev/changelog/post/2025-08-05-sandbox-sdk-major-update/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) We’ve shipped a major release for the [@cloudflare/sandbox ↗](https://github.com/cloudflare/sandbox-sdk) SDK, turning it into a full-featured, container-based execution platform that runs securely on Cloudflare Workers. This update adds live streaming of output, persistent Python and JavaScript code interpreters with rich output support (charts, tables, HTML, JSON), file system access, Git operations, full background process control, and the ability to expose running services via public URLs. This makes it ideal for building AI agents, CI runners, cloud REPLs, data analysis pipelines, or full developer tools — all without managing infrastructure. #### Code interpreter (Python, JS, TS) Create persistent code contexts with support for rich visual + structured outputs. #### createCodeContext(options) Creates a new code execution context with persistent state. **TypeScript** ```ts // Create a Python context const pythonCtx = await sandbox.createCodeContext({ language: "python" }); // Create a JavaScript context const jsCtx = await sandbox.createCodeContext({ language: "javascript" }); ``` Options: * language: Programming language ('python' | 'javascript' | 'typescript') * cwd: Working directory (default: /workspace) * envVars: Environment variables for the context #### runCode(code, options) Executes code with optional streaming callbacks. **TypeScript** ```ts // Simple execution const execution = await sandbox.runCode('print("Hello World")', { context: pythonCtx, }); // With streaming callbacks await sandbox.runCode( ` for i in range(5): print(f"Step {i}") time.sleep(1) `, { context: pythonCtx, onStdout: (output) => console.log("Real-time:", output.text), onResult: (result) => console.log("Result:", result), }, ); ``` Options: * language: Programming language ('python' | 'javascript' | 'typescript') * cwd: Working directory (default: /workspace) * envVars: Environment variables for the context #### Real-time streaming output Returns a streaming response for real-time processing. **TypeScript** ```ts const stream = await sandbox.runCodeStream( "import time; [print(i) for i in range(10)]", ); // Process the stream as needed ``` #### Rich output handling Interpreter outputs are auto-formatted and returned in multiple formats: * text * html (e.g., Pandas tables) * png, svg (e.g., Matplotlib charts) * json (structured data) * chart (parsed visualizations) **TypeScript** ```ts const result = await sandbox.runCode( ` import seaborn as sns import matplotlib.pyplot as plt data = sns.load_dataset("flights") pivot = data.pivot("month", "year", "passengers") sns.heatmap(pivot, annot=True, fmt="d") plt.title("Flight Passengers") plt.show() pivot.to_dict() `, { context: pythonCtx }, ); if (result.png) { console.log("Chart output:", result.png); } ``` #### Preview URLs from Exposed Ports Start background processes and expose them with live URLs. **TypeScript** ```ts await sandbox.startProcess("python -m http.server 8000"); const preview = await sandbox.exposePort(8000); console.log("Live preview at:", preview.url); ``` #### Full process lifecycle control Start, inspect, and terminate long-running background processes. **TypeScript** ```ts const process = await sandbox.startProcess("node server.js"); console.log(`Started process ${process.id} with PID ${process.pid}`); // Monitor the process const logStream = await sandbox.streamProcessLogs(process.id); for await (const log of parseSSEStream(logStream)) { console.log(`Server: ${log.data}`); } ``` * listProcesses() - List all running processes * getProcess(id) - Get detailed process status * killProcess(id, signal) - Terminate specific processes * killAllProcesses() - Kill all processes * streamProcessLogs(id, options) - Stream logs from running processes * getProcessLogs(id) - Get accumulated process output #### Git integration Clone Git repositories directly into the sandbox. **TypeScript** ```ts await sandbox.gitCheckout("https://github.com/user/repo", { branch: "main", targetDir: "my-project", }); ``` Sandboxes are still experimental. We're using them to explore how isolated, container-like workloads might scale on Cloudflare — and to help define the developer experience around them. Aug 05, 2025 1. ### [OpenAI open models now available on Workers AI](https://edgetunnel-b2h.pages.dev/changelog/post/2025-08-05-openai-open-models/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers AI ](https://edgetunnel-b2h.pages.dev/workers-ai/) We're thrilled to be a Day 0 partner with [OpenAI ↗](http://openai.com/index/introducing-gpt-oss) to bring their [latest open models ↗](https://openai.com/index/gpt-oss-model-card/) to Workers AI, including support for Responses API, Code Interpreter, and Web Search (coming soon). Get started with the new models at `@cf/openai/gpt-oss-120b` and `@cf/openai/gpt-oss-20b`. Check out the [blog ↗](https://blog.cloudflare.com/openai-gpt-oss-on-workers-ai) for more details about the new models, and the [gpt-oss-120b](https://edgetunnel-b2h.pages.dev/workers-ai/models/gpt-oss-120b) and [gpt-oss-20b](https://edgetunnel-b2h.pages.dev/workers-ai/models/gpt-oss-20b) model pages for more information about pricing and context windows. #### Responses API If you call the model through: * Workers Binding, it will accept/return Responses API – `env.AI.run(“@cf/openai/gpt-oss-120b”)` * REST API on `/run` endpoint, it will accept/return Responses API – `https://api.cloudflare.com/client/v4/accounts//ai/run/@cf/openai/gpt-oss-120b` * REST API on new `/responses` endpoint, it will accept/return Responses API – `https://api.cloudflare.com/client/v4/accounts//ai/v1/responses` * REST API for OpenAI Compatible endpoint, it will return Chat Completions (coming soon) – `https://api.cloudflare.com/client/v4/accounts//ai/v1/chat/completions` ```plaintext curl https://api.cloudflare.com/client/v4/accounts//ai/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $CLOUDFLARE_API_KEY" \ -d '{ "model": "@cf/openai/gpt-oss-120b", "reasoning": {"effort": "medium"}, "input": [ { "role": "user", "content": "What are the benefits of open-source models?" } ] }' ``` #### Code Interpreter The model is natively trained to support stateful code execution, and we've implemented support for this feature using our [Sandbox SDK ↗](https://github.com/cloudflare/sandbox-sdk) and [Containers ↗](https://blog.cloudflare.com/containers-are-available-in-public-beta-for-simple-global-and-programmable/). Cloudflare's Developer Platform is uniquely positioned to support this feature, so we're very excited to bring our products together to support this new use case. #### Web Search (coming soon) We are working to implement Web Search for the model, where users can bring their own Exa API Key so the model can browse the Internet. Jul 28, 2025 1. ### [Introducing pricing for the Browser Rendering API — $0.09 per browser hour](https://edgetunnel-b2h.pages.dev/changelog/post/2025-07-28-br-pricing/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) We’ve launched pricing for [Browser Rendering](https://edgetunnel-b2h.pages.dev/browser-run/), including a free tier and a pay-as-you-go model that scales with your needs. Starting **August 20, 2025**, Cloudflare will begin billing for Browser Rendering. There are two ways to use Browser Rendering. Depending on the method you use, here’s how billing will work: * [**REST API**](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/): Charged for **Duration** only ($/browser hour) * [**Browser Sessions**](https://edgetunnel-b2h.pages.dev/browser-run/#integration-methods): Charged for both **Duration** and **Concurrency** ($/browser hour and # of concurrent browsers) Included usage and pricing by plan | Plan | Included duration | Included concurrency | Price (beyond included) | | ---------------- | ------------------ | ----------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Workers Free** | 10 minutes per day | 3 concurrent browsers | N/A | | **Workers Paid** | 10 hours per month | 10 concurrent browsers (averaged monthly) | **1\. REST API**: $0.09 per additional browser hour **2\. Workers Bindings**: $0.09 per additional browser hour $2.00 per additional concurrent browser | What you need to know: * **Workers Free Plan:** 10 minutes of browser usage per day with 3 concurrent browsers at no charge. * **Workers Paid Plan:** 10 hours of browser usage per month with 10 concurrent browsers (averaged monthly) at no charge. Additional usage is charged as shown above. You can monitor usage via the [Cloudflare dashboard ↗](https://dash.cloudflare.com/?to=/:account/workers/browser-run). Go to **Compute** \> **Browser Run**. ![Browser Rendering dashboard](https://edgetunnel-b2h.pages.dev/_astro/dashboard.BQnX87lT_39GAT.webp) If you've been using Browser Rendering and do not wish to incur charges, ensure your usage stays within your plan's [included usage](https://edgetunnel-b2h.pages.dev/browser-run/pricing/). To estimate costs, take a look at these [example pricing scenarios](https://edgetunnel-b2h.pages.dev/browser-run/pricing/#examples-of-workers-paid-pricing). Jul 22, 2025 1. ### [Browser Rendering now supports local development](https://edgetunnel-b2h.pages.dev/changelog/post/2025-07-22-br-local-dev/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) You can now run your Browser Rendering locally using `npx wrangler dev`, which spins up a browser directly on your machine before deploying to Cloudflare's global network. By running tests locally, you can quickly develop, debug, and test changes without needing to deploy or worry about usage costs. Get started with this [example guide](https://edgetunnel-b2h.pages.dev/browser-run/how-to/deploy-worker/) that shows how to use Cloudflare's [fork of Puppeteer](https://edgetunnel-b2h.pages.dev/browser-run/puppeteer/) (you can also use [Playwright](https://edgetunnel-b2h.pages.dev/browser-run/playwright/)) to take screenshots of webpages and store the results in [Workers KV](https://edgetunnel-b2h.pages.dev/kv/). Jul 08, 2025 1. ### [Faster indexing and new Jobs view in AutoRAG](https://edgetunnel-b2h.pages.dev/changelog/post/2025-07-08-autorag-jobs-view/) [ AI Search ](https://edgetunnel-b2h.pages.dev/ai-search/) You can now expect **3-5× faster indexing** in AutoRAG, and with it, a brand new **Jobs view** to help you monitor indexing progress. With each AutoRAG, indexing jobs are automatically triggered to sync your data source (i.e. R2 bucket) with your Vectorize index, ensuring new or updated files are reflected in your query results. You can also trigger jobs manually via the [Sync API](https://edgetunnel-b2h.pages.dev/api/resources/ai-search/subresources/rags/) or by clicking “Sync index” in the dashboard. With the new jobs observability, you can now: * View the status, job ID, source, start time, duration and last sync time for each indexing job * Inspect real-time logs of job events (e.g. `Starting indexing data source...`) * See a history of past indexing jobs under the Jobs tab of your AutoRAG This makes it easier to understand what’s happening behind the scenes. **Coming soon:** We’re adding APIs to programmatically check indexing status, making it even easier to integrate AutoRAG into your workflows. Try it out today on the [Cloudflare dashboard ↗](https://dash.cloudflare.com/?to=/:account/ai/autorag). Jul 01, 2025 1. ### [Introducing Pay Per Crawl (private beta)](https://edgetunnel-b2h.pages.dev/changelog/post/2025-07-01-pay-per-crawl/) [ AI Crawl Control ](https://edgetunnel-b2h.pages.dev/ai-crawl-control/) We are introducing a new feature of [AI Crawl Control](https://edgetunnel-b2h.pages.dev/ai-crawl-control/) — Pay Per Crawl. [Pay Per Crawl](https://edgetunnel-b2h.pages.dev/ai-crawl-control/features/pay-per-crawl/what-is-pay-per-crawl/) enables site owners to require payment from AI crawlers every time the crawlers access their content, thereby fostering a fairer Internet by enabling site owners to control and monetize how their content gets used by AI. ![Pay per crawl](https://edgetunnel-b2h.pages.dev/_astro/pay-per-crawl.B5bv2nwT_1TH6vv.webp) **For Site Owners:** * Set pricing and select which crawlers to charge for content access * Manage payments via Stripe * Monitor analytics on successful content deliveries **For AI Crawler Owners:** * Use HTTP headers to request and accept pricing * Receive clear confirmations on charges for accessed content Learn more in the [Pay Per Crawl documentation](https://edgetunnel-b2h.pages.dev/ai-crawl-control/features/pay-per-crawl/what-is-pay-per-crawl/). Jul 01, 2025 1. ### [AI Crawl Control refresh](https://edgetunnel-b2h.pages.dev/changelog/post/2025-07-01-refresh/) [ AI Crawl Control ](https://edgetunnel-b2h.pages.dev/ai-crawl-control/) We redesigned the AI Crawl Control dashboard to provide more intuitive and granular control over AI crawlers. * From the new **AI Crawlers** tab: block specific AI crawlers. * From the new **Metrics** tab: view AI Crawl Control metrics. ![Block AI crawlers](https://edgetunnel-b2h.pages.dev/_astro/manage-ai-crawlers.6UgS8dSG_Z1HRWpI.webp) ![Analyze AI crawler activity](https://edgetunnel-b2h.pages.dev/_astro/analyze-metrics.C52pJZVg_1C7hti.webp) To get started, explore: * [Manage AI crawlers](https://edgetunnel-b2h.pages.dev/ai-crawl-control/features/manage-ai-crawlers/). * [Analyze AI traffic](https://edgetunnel-b2h.pages.dev/ai-crawl-control/features/analyze-ai-traffic/). Jun 25, 2025 1. ### [Run AI-generated code on-demand with Code Sandboxes (new)](https://edgetunnel-b2h.pages.dev/changelog/post/2025-06-24-announcing-sandboxes/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/)[ Workflows ](https://edgetunnel-b2h.pages.dev/workflows/) AI is supercharging app development for everyone, but we need a safe way to run untrusted, LLM-written code. We’re introducing [Sandboxes ↗](https://www.npmjs.com/package/@cloudflare/sandbox), which let your Worker run actual processes in a secure, container-based environment. **TypeScript** ```ts import { getSandbox } from "@cloudflare/sandbox"; export { Sandbox } from "@cloudflare/sandbox"; export default { async fetch(request: Request, env: Env) { const sandbox = getSandbox(env.Sandbox, "my-sandbox"); return sandbox.exec("ls", ["-la"]); }, }; ``` #### Methods * `exec(command: string, args: string[], options?: { stream?: boolean })`:Execute a command in the sandbox. * `gitCheckout(repoUrl: string, options: { branch?: string; targetDir?: string; stream?: boolean })`: Checkout a git repository in the sandbox. * `mkdir(path: string, options: { recursive?: boolean; stream?: boolean })`: Create a directory in the sandbox. * `writeFile(path: string, content: string, options: { encoding?: string; stream?: boolean })`: Write content to a file in the sandbox. * `readFile(path: string, options: { encoding?: string; stream?: boolean })`: Read content from a file in the sandbox. * `deleteFile(path: string, options?: { stream?: boolean })`: Delete a file from the sandbox. * `renameFile(oldPath: string, newPath: string, options?: { stream?: boolean })`: Rename a file in the sandbox. * `moveFile(sourcePath: string, destinationPath: string, options?: { stream?: boolean })`: Move a file from one location to another in the sandbox. * `ping()`: Ping the sandbox. Sandboxes are still experimental. We're using them to explore how isolated, container-like workloads might scale on Cloudflare — and to help define the developer experience around them. You can try it today from your Worker, with just a few lines of code. Let us know what you build. Jun 19, 2025 1. ### [View custom metadata in responses and guide AI-search with context in AutoRAG](https://edgetunnel-b2h.pages.dev/changelog/post/2025-06-19-autorag-custom-metadata-and-context/) [ AI Search ](https://edgetunnel-b2h.pages.dev/ai-search/) In [AutoRAG](https://edgetunnel-b2h.pages.dev/ai-search/), you can now view your object's custom metadata in the response from [/search](https://edgetunnel-b2h.pages.dev/ai-search/api/search/workers-binding/) and [/ai-search](https://edgetunnel-b2h.pages.dev/ai-search/api/search/workers-binding/), and optionally add a `context` field in the custom metadata of an object to provide additional guidance for AI-generated answers. You can add [custom metadata](https://edgetunnel-b2h.pages.dev/r2/api/workers/workers-api-reference/#r2putoptions) to an object when uploading it to your R2 bucket. #### Object's custom metadata in search responses When you run a search, AutoRAG now returns any custom metadata associated with the object. This metadata appears in the response inside `attributes` then `file` , and can be used for downstream processing. For example, the `attributes` section of your search response may look like: ```json { "attributes": { "timestamp": 1750001460000, "folder": "docs/", "filename": "launch-checklist.md", "file": { "url": "https://wiki.company.com/docs/launch-checklist", "context": "A checklist for internal launch readiness, including legal, engineering, and marketing steps." } } } ``` #### Add a `context` field to guide LLM answers When you include a custom metadata field named `context`, AutoRAG attaches that value to each chunk of the file. When you run an `/ai-search` query, this `context` is passed to the LLM and can be used as additional input when generating an answer. We recommend using the `context` field to describe supplemental information you want the LLM to consider, such as a summary of the document or a source URL. If you have several different metadata attributes, you can join them together however you choose within the `context` string. For example: ```json { "context": "summary: 'Checklist for internal product launch readiness, including legal, engineering, and marketing steps.'; url: 'https://wiki.company.com/docs/launch-checklist'" } ``` This gives you more control over how your content is interpreted, without requiring you to modify the original contents of the file. Learn more in AutoRAG's [metadata filtering documentation](https://edgetunnel-b2h.pages.dev/ai-search/configuration/indexing/metadata/). Jun 19, 2025 1. ### [Filter your AutoRAG search by file name](https://edgetunnel-b2h.pages.dev/changelog/post/2025-06-19-autorag-filename-filter/) [ AI Search ](https://edgetunnel-b2h.pages.dev/ai-search/) In [AutoRAG](https://edgetunnel-b2h.pages.dev/ai-search/), you can now [filter](https://edgetunnel-b2h.pages.dev/ai-search/configuration/indexing/metadata/) by an object's file name using the `filename` attribute, giving you more control over which files are searched for a given query. This is useful when your application has already determined which files should be searched. For example, you might query a PostgreSQL database to get a list of files a user has access to based on their permissions, and then use that list to limit what AutoRAG retrieves. For example, your search query may look like: **JavaScript** ```js const response = await env.AI.autorag("my-autorag").search({ query: "what is the project deadline?", filters: { type: "eq", key: "filename", value: "project-alpha-roadmap.md", }, }); ``` This allows you to connect your application logic with AutoRAG's retrieval process, making it easy to control what gets searched without needing to reindex or modify your data. Learn more in AutoRAG's [metadata filtering documentation](https://edgetunnel-b2h.pages.dev/ai-search/configuration/indexing/metadata/). Jun 03, 2025 1. ### [AI Gateway adds OpenAI compatible endpoint](https://edgetunnel-b2h.pages.dev/changelog/post/2025-06-03-aig-openai-compatible-endpoint/) [ AI Gateway ](https://edgetunnel-b2h.pages.dev/ai-gateway/) Users can now use an [OpenAI Compatible endpoint](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/chat-completion/) in AI Gateway to easily switch between providers, while keeping the exact same request and response formats. We're launching now with the chat completions endpoint, with the embeddings endpoint coming up next. To get started, use the OpenAI compatible chat completions endpoint URL with your own account id and gateway id and switch between providers by changing the `model` and `apiKey` parameters. **OpenAI SDK Example** ```js import OpenAI from "openai"; const client = new OpenAI({ apiKey: "YOUR_PROVIDER_API_KEY", // Provider API key baseURL: "https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat", }); const response = await client.chat.completions.create({ model: "google-ai-studio/gemini-2.0-flash", messages: [{ role: "user", content: "What is Cloudflare?" }], }); console.log(response.choices[0].message.content); ``` Additionally, the [OpenAI Compatible endpoint](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/chat-completion/) can be combined with our [Universal Endpoint](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/universal/) to add fallbacks across multiple providers. That means AI Gateway will return every response in the same standardized format, no extra parsing logic required! Learn more in the [OpenAI Compatibility](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/chat-completion/) documentation. May 28, 2025 1. ### [Playwright MCP server is now compatible with Browser Rendering](https://edgetunnel-b2h.pages.dev/changelog/post/2025-05-28-playwright-mcp/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) We're excited to share that you can now use the [Playwright MCP ↗](https://github.com/cloudflare/playwright-mcp) server with Browser Rendering. Once you [deploy the server](https://edgetunnel-b2h.pages.dev/browser-run/playwright/playwright-mcp/#deploying), you can use any MCP client with it to interact with Browser Rendering. This allows you to run AI models that can automate browser tasks, such as taking screenshots, filling out forms, or scraping data. ![Access Analytics](https://edgetunnel-b2h.pages.dev/_astro/playground-ai-screenshot.v44jFMBu_Z1xgc6e.webp) Playwright MCP is available as an npm package at [@cloudflare/playwright-mcp ↗](https://www.npmjs.com/package/@cloudflare/playwright-mcp). To install it, type: npm yarn pnpm bun ``` npm i -D @cloudflare/playwright-mcp ``` ``` yarn add -D @cloudflare/playwright-mcp ``` ``` pnpm add -D @cloudflare/playwright-mcp ``` ``` bun add -d @cloudflare/playwright-mcp ``` Deploying the server is then as easy as: **TypeScript** ```ts import { env } from "cloudflare:workers"; import { createMcpAgent } from "@cloudflare/playwright-mcp"; export const PlaywrightMCP = createMcpAgent(env.BROWSER); export default PlaywrightMCP.mount("/sse"); ``` Check out the full code at [GitHub ↗](https://github.com/cloudflare/playwright-mcp). Learn more about Playwright MCP in our [documentation](https://edgetunnel-b2h.pages.dev/browser-run/playwright/playwright-mcp/). Apr 23, 2025 1. ### [Metadata filtering and multitenancy support in AutoRAG](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-23-autorag-metadata-filtering/) [ AI Search ](https://edgetunnel-b2h.pages.dev/ai-search/) You can now filter [AutoRAG](https://edgetunnel-b2h.pages.dev/ai-search/) search results by `folder` and `timestamp` using [metadata filtering](https://edgetunnel-b2h.pages.dev/ai-search/configuration/indexing/metadata/) to narrow down the scope of your query. This makes it easy to build [multitenant experiences](https://edgetunnel-b2h.pages.dev/ai-search/how-to/per-tenant-search/) where each user can only access their own data. By organizing your content into per-tenant folders and applying a `folder` filter at query time, you ensure that each tenant retrieves only their own documents. **Example folder structure:** ```bash customer-a/logs/ customer-a/contracts/ customer-b/contracts/ ``` **Example query:** **JavaScript** ```js const response = await env.AI.autorag("my-autorag").search({ query: "When did I sign my agreement contract?", filters: { type: "eq", key: "folder", value: "customer-a/contracts/", }, }); ``` You can use metadata filtering by creating a new AutoRAG or reindexing existing data. To reindex all content in an existing AutoRAG, update any chunking setting and select **Sync index**. Metadata filtering is available for all data indexed on or after **April 21, 2025**. If you are new to AutoRAG, get started with the [Get started AutoRAG guide](https://edgetunnel-b2h.pages.dev/ai-search/get-started/). Apr 11, 2025 1. ### [Workers AI for Developer Week - faster inference, new models, async batch API, expanded LoRA support](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-11-new-models-faster-inference/) [ Workers AI ](https://edgetunnel-b2h.pages.dev/workers-ai/) Happy Developer Week 2025! Workers AI is excited to announce a couple of new features and improvements available today. Check out our [blog ↗](https://blog.cloudflare.com/workers-ai-improvements) for all the announcement details. #### Faster inference + New models We’re rolling out some in-place improvements to our models that can help speed up inference by 2-4x! Users of the models below will enjoy an automatic speed boost starting today: * [@cf/meta/llama-3.3-70b-instruct-fp8-fast](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-3.3-70b-instruct-fp8-fast/) gets a speed boost of 2-4x, leveraging techniques like speculative decoding, prefix caching, and an updated inference backend. * [@cf/baai/bge-small-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-small-en-v1.5/), [@cf/baai/bge-base-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-base-en-v1.5/), [@cf/baai/bge-large-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-large-en-v1.5/) get an updated back end, which should improve inference times by 2x. * With the `bge` models, we’re also announcing a new parameter called `pooling` which can take `cls` or `mean` as options. We highly recommend using `pooling: cls` which will help generate more accurate embeddings. However, embeddings generated with cls pooling are not backwards compatible with mean pooling. For this to not be a breaking change, the default remains as mean pooling. Please specify `pooling: cls` to enjoy more accurate embeddings going forward. We’re also excited to launch a few new models in our catalog to help round out your experience with Workers AI. We’ll be deprecating some older models in the future, so stay tuned for a deprecation announcement. Today’s new models include: * [@cf/mistralai/mistral-small-3.1-24b-instruct](https://edgetunnel-b2h.pages.dev/workers-ai/models/mistral-small-3.1-24b-instruct/): a 24B parameter model achieving state-of-the-art capabilities comparable to larger models, with support for vision and tool calling. * [@cf/google/gemma-3-12b-it](https://edgetunnel-b2h.pages.dev/workers-ai/models/gemma-3-12b-it/): well-suited for a variety of text generation and image understanding tasks, including question answering, summarization and reasoning, with a 128K context window, and multilingual support in over 140 languages. * [@cf/qwen/qwq-32b](https://edgetunnel-b2h.pages.dev/workers-ai/models/qwq-32b/): a medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini. * [@cf/qwen/qwen2.5-coder-32b-instruct](https://edgetunnel-b2h.pages.dev/workers-ai/models/qwen2.5-coder-32b-instruct/): the current state-of-the-art open-source code LLM, with its coding abilities matching those of GPT-4o. #### Batch Inference Introducing a new batch inference feature that allows you to send us an array of requests, which we will fulfill as fast as possible and send them back as an array. This is really helpful for large workloads such as summarization, embeddings, etc. where you don’t have a human-in-the-loop. Using the batch API will guarantee that your requests are fulfilled eventually, rather than erroring out if we don’t have enough capacity at a given time. Check out the [tutorial](https://edgetunnel-b2h.pages.dev/workers-ai/features/batch-api/) to get started! Models that support batch inference today include: * [@cf/meta/llama-3.3-70b-instruct-fp8-fast](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-3.3-70b-instruct-fp8-fast/) * [@cf/baai/bge-small-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-small-en-v1.5/) * [@cf/baai/bge-base-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-base-en-v1.5/) * [@cf/baai/bge-large-en-v1.5](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-large-en-v1.5/) * [@cf/baai/bge-m3](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-m3/) * [@cf/meta/m2m100-1.2b](https://edgetunnel-b2h.pages.dev/workers-ai/models/m2m100-1.2b/) #### Expanded LoRA support We’ve upgraded our LoRA experience to include 8 newer models, and can support ranks of up to 32 with a 300MB safetensors file limit (previously limited to rank of 8 and 100MB safetensors) Check out our [LoRAs page](https://edgetunnel-b2h.pages.dev/workers-ai/features/fine-tunes/loras/) to get started. Models that support LoRAs now include: * [@cf/meta/llama-3.2-11b-vision-instruct](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-3.2-11b-vision-instruct/) * [@cf/meta/llama-3.3-70b-instruct-fp8-fast](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-3.3-70b-instruct-fp8-fast/) * [@cf/meta/llama-guard-3-8b](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-guard-3-8b/) * [@cf/meta/llama-3.1-8b-instruct-fast](https://edgetunnel-b2h.pages.dev/workers-ai/models/llama-3.1-8b-instruct-fast/) (coming soon) * [@cf/deepseek-ai/deepseek-r1-distill-qwen-32b](https://edgetunnel-b2h.pages.dev/workers-ai/models/deepseek-r1-distill-qwen-32b/) (coming soon) * [@cf/qwen/qwen2.5-coder-32b-instruct](https://edgetunnel-b2h.pages.dev/workers-ai/models/qwen2.5-coder-32b-instruct/) * [@cf/qwen/qwq-32b](https://edgetunnel-b2h.pages.dev/workers-ai/models/qwq-32b/) * [@cf/mistralai/mistral-small-3.1-24b-instruct](https://edgetunnel-b2h.pages.dev/workers-ai/models/mistral-small-3.1-24b-instruct/) * [@cf/google/gemma-3-12b-it](https://edgetunnel-b2h.pages.dev/workers-ai/models/gemma-3-12b-it/) Apr 07, 2025 1. ### [Build MCP servers with the Agents SDK](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-07-mcp-servers-agents-sdk-updates/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) The Agents SDK now includes built-in support for building remote MCP (Model Context Protocol) servers directly as part of your Agent. This allows you to easily create and manage MCP servers, without the need for additional infrastructure or configuration. The SDK includes a new `MCPAgent` class that extends the `Agent` class and allows you to expose resources and tools over the MCP protocol, as well as authorization and authentication to enable remote MCP servers. * [ JavaScript ](#tab-panel-3730) * [ TypeScript ](#tab-panel-3731) **JavaScript** ```js export class MyMCP extends McpAgent { server = new McpServer({ name: "Demo", version: "1.0.0", }); async init() { this.server.resource(`counter`, `mcp://resource/counter`, (uri) => { // ... }); this.server.tool( "add", "Add two numbers together", { a: z.number(), b: z.number() }, async ({ a, b }) => { // ... }, ); } } ``` **TypeScript** ```ts export class MyMCP extends McpAgent { server = new McpServer({ name: "Demo", version: "1.0.0", }); async init() { this.server.resource(`counter`, `mcp://resource/counter`, (uri) => { // ... }); this.server.tool( "add", "Add two numbers together", { a: z.number(), b: z.number() }, async ({ a, b }) => { // ... }, ); } } ``` See [the example ↗](https://github.com/cloudflare/agents/tree/main/examples/mcp) for the full code and as the basis for building your own MCP servers, and the [client example ↗](https://github.com/cloudflare/agents/tree/main/examples/mcp-client) for how to build an Agent that acts as an MCP client. To learn more, review the [announcement blog ↗](https://blog.cloudflare.com/building-ai-agents-with-mcp-authn-authz-and-durable-objects) as part of Developer Week 2025. #### Agents SDK updates We've made a number of improvements to the [Agents SDK](https://edgetunnel-b2h.pages.dev/agents/), including: * Support for building MCP servers with the new `MCPAgent` class. * The ability to export the current agent, request and WebSocket connection context using `import { context } from "agents"`, allowing you to minimize or avoid direct dependency injection when calling tools. * Fixed a bug that prevented query parameters from being sent to the Agent server from the `useAgent` React hook. * Automatically converting the `agent` name in `useAgent` or `useAgentChat` to kebab-case to ensure it matches the naming convention expected by [routeAgentRequest](https://edgetunnel-b2h.pages.dev/agents/runtime/communication/routing/). To install or update the Agents SDK, run `npm i agents@latest` in an existing project, or explore the `agents-starter` project: ```sh npm create cloudflare@latest -- --template cloudflare/agents-starter ``` See the full release notes and changelog [on the Agents SDK repository ↗](https://github.com/cloudflare/agents/blob/main/packages/agents/CHANGELOG.md) and Apr 07, 2025 1. ### [Create fully-managed RAG pipelines for your AI applications with AutoRAG](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-07-autorag-open-beta/) [ AI Search ](https://edgetunnel-b2h.pages.dev/ai-search/)[ Vectorize ](https://edgetunnel-b2h.pages.dev/vectorize/) [AutoRAG](https://edgetunnel-b2h.pages.dev/ai-search/) is now in open beta, making it easy for you to build fully-managed retrieval-augmented generation (RAG) pipelines without managing infrastructure. Just upload your docs to [R2](https://edgetunnel-b2h.pages.dev/r2/get-started/), and AutoRAG handles the rest: embeddings, indexing, retrieval, and response generation via API. With AutoRAG, you can: * **Customize your pipeline:** Choose from [Workers AI](https://edgetunnel-b2h.pages.dev/workers-ai) models, configure chunking strategies, edit system prompts, and more. * **Instant setup:** AutoRAG provisions everything you need from [Vectorize](https://edgetunnel-b2h.pages.dev/vectorize), [AI gateway](https://edgetunnel-b2h.pages.dev/ai-gateway), to pipeline logic for you, so you can go from zero to a working RAG pipeline in seconds. * **Keep your index fresh:** AutoRAG continuously syncs your index with your data source to ensure responses stay accurate and up to date. * **Ask questions:** Query your data and receive grounded responses via a [Workers binding](https://edgetunnel-b2h.pages.dev/ai-search/api/search/workers-binding/) or [API](https://edgetunnel-b2h.pages.dev/ai-search/api/search/rest-api/). Whether you're building internal tools, AI-powered search, or a support assistant, AutoRAG gets you from idea to deployment in minutes. Get started in the [Cloudflare dashboard ↗](https://dash.cloudflare.com/?to=/:account/ai/autorag) or check out the [guide](https://edgetunnel-b2h.pages.dev/ai-search/get-started/) for instructions on how to build your RAG pipeline today. Apr 07, 2025 1. ### [Browser Rendering REST API is Generally Available, with new endpoints and a free tier](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-07-br-free-ga-playwright/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) We’re excited to announce Browser Rendering is now available on the [Workers Free plan ↗](https://www.cloudflare.com/plans/developer-platform/), making it even easier to prototype and experiment with web search and headless browser use-cases when building applications on Workers. The Browser Rendering **[REST API](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/) is now Generally Available**, allowing you to control browser instances from outside of Workers applications. We've added three new endpoints to help automate more browser tasks: * **Extract structured data** – Use `/json` to retrieve structured data from a webpage. * **Retrieve links** – Use `/links` to pull all links from a webpage. * **Convert to Markdown** – Use `/markdown` to convert webpage content into Markdown format. For example, to fetch the Markdown representation of a webpage: **Markdown example** ```bash curl -X 'POST' 'https://api.cloudflare.com/client/v4/accounts//browser-rendering/markdown' \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer ' \ -d '{ "url": "https://example.com" }' ``` For the full list of endpoints, check out our [REST API documentation](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/). You can also interact with Browser Rendering via the [Cloudflare TypeScript SDK ↗](https://github.com/cloudflare/cloudflare-typescript). We also recently landed support for [Playwright](https://edgetunnel-b2h.pages.dev/browser-run/playwright/) in Browser Rendering for browser automation from Cloudflare [Workers](https://edgetunnel-b2h.pages.dev/workers/), in addition to [Puppeteer](https://edgetunnel-b2h.pages.dev/browser-run/puppeteer/), giving you more flexibility to test across different browser environments. Visit the [Browser Rendering docs](https://edgetunnel-b2h.pages.dev/browser-run/) to learn more about how to use headless browsers in your applications. Apr 04, 2025 1. ### [Playwright for Browser Rendering now available](https://edgetunnel-b2h.pages.dev/changelog/post/2025-04-04-playwright-beta/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) We're excited to share that you can now use Playwright's browser automation [capabilities ↗](https://playwright.dev/docs/api/class-playwright) from Cloudflare [Workers](https://edgetunnel-b2h.pages.dev/workers/). [Playwright ↗](https://playwright.dev/) is an open-source package developed by Microsoft that can do browser automation tasks; it's commonly used to write software tests, debug applications, create screenshots, and crawl pages. Like [Puppeteer](https://edgetunnel-b2h.pages.dev/browser-run/puppeteer/), we [forked ↗](https://github.com/cloudflare/playwright) Playwright and modified it to be compatible with Cloudflare Workers and [Browser Rendering](https://edgetunnel-b2h.pages.dev/browser-run/). Below is an example of how to use Playwright with Browser Rendering to test a TODO application using assertions: **Assertion example** ```ts import { launch, type BrowserWorker } from "@cloudflare/playwright"; import { expect } from "@cloudflare/playwright/test"; interface Env { MYBROWSER: BrowserWorker; } export default { async fetch(request: Request, env: Env) { const browser = await launch(env.MYBROWSER); const page = await browser.newPage(); await page.goto("https://demo.playwright.dev/todomvc"); const TODO_ITEMS = [ "buy some cheese", "feed the cat", "book a doctors appointment", ]; const newTodo = page.getByPlaceholder("What needs to be done?"); for (const item of TODO_ITEMS) { await newTodo.fill(item); await newTodo.press("Enter"); } await expect(page.getByTestId("todo-title")).toHaveCount(TODO_ITEMS.length); await Promise.all( TODO_ITEMS.map((value, index) => expect(page.getByTestId("todo-title").nth(index)).toHaveText(value), ), ); }, }; ``` Playwright is available as an npm package at [@cloudflare/playwright ↗](https://www.npmjs.com/package/@cloudflare/playwright) and the code is at [GitHub ↗](https://github.com/cloudflare/playwright). Learn more in our [documentation](https://edgetunnel-b2h.pages.dev/browser-run/playwright/). Mar 21, 2025 1. ### [AI Gateway launches Realtime WebSockets API](https://edgetunnel-b2h.pages.dev/changelog/post/2025-03-20-websockets/) [ AI Gateway ](https://edgetunnel-b2h.pages.dev/ai-gateway/) We are excited to announce that [AI Gateway](https://edgetunnel-b2h.pages.dev/ai-gateway/) now supports real-time AI interactions with the new [Realtime WebSockets API](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/websockets-api/realtime-api/). This new capability allows developers to establish persistent, low-latency connections between their applications and AI models, enabling natural, real-time conversational AI experiences, including speech-to-speech interactions. The Realtime WebSockets API works with the [OpenAI Realtime API ↗](https://platform.openai.com/docs/guides/realtime#connect-with-websockets), [Google Gemini Live API ↗](https://ai.google.dev/gemini-api/docs/multimodal-live), and supports real-time text and speech interactions with models from [Cartesia ↗](https://docs.cartesia.ai/api-reference/tts/tts), and [ElevenLabs ↗](https://elevenlabs.io/docs/conversational-ai/api-reference/conversational-ai/websocket). Here's how you can connect AI Gateway to [OpenAI's Realtime API ↗](https://platform.openai.com/docs/guides/realtime#connect-with-websockets) using WebSockets: **OpenAI Realtime API example** ```javascript import WebSocket from "ws"; const url = "wss://gateway.ai.cloudflare.com/v1///openai?model=gpt-4o-realtime-preview-2024-12-17"; const ws = new WebSocket(url, { headers: { "cf-aig-authorization": process.env.CLOUDFLARE_API_KEY, Authorization: "Bearer " + process.env.OPENAI_API_KEY, "OpenAI-Beta": "realtime=v1", }, }); ws.on("open", () => console.log("Connected to server.")); ws.on("message", (message) => console.log(JSON.parse(message.toString()))); ws.send( JSON.stringify({ type: "response.create", response: { modalities: ["text"], instructions: "Tell me a joke" }, }), ); ``` Get started by checking out the [Realtime WebSockets API](https://edgetunnel-b2h.pages.dev/ai-gateway/usage/websockets-api/realtime-api/) documentation. Mar 20, 2025 1. ### [Markdown conversion in Workers AI](https://edgetunnel-b2h.pages.dev/changelog/post/2025-03-20-markdown-conversion/) [ Workers AI ](https://edgetunnel-b2h.pages.dev/workers-ai/) Document conversion plays an important role when designing and developing AI applications and agents. Workers AI now provides the `toMarkdown` utility method that developers can use to for quick, easy, and convenient conversion and summary of documents in multiple formats to Markdown language. You can call this new tool using a binding by calling `env.AI.toMarkdown()` or the using the [REST API](https://edgetunnel-b2h.pages.dev/api/resources/ai/) endpoint. In this example, we fetch a PDF document and an image from R2 and feed them both to `env.AI.toMarkdown()`. The result is a list of converted documents. Workers AI models are used automatically to detect and summarize the image. **TypeScript** ```typescript import { Env } from "./env"; export default { async fetch(request: Request, env: Env, ctx: ExecutionContext) { // https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/somatosensory.pdf const pdf = await env.R2.get("somatosensory.pdf"); // https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/cat.jpeg const cat = await env.R2.get("cat.jpeg"); return Response.json( await env.AI.toMarkdown([ { name: "somatosensory.pdf", blob: new Blob([await pdf.arrayBuffer()], { type: "application/octet-stream", }), }, { name: "cat.jpeg", blob: new Blob([await cat.arrayBuffer()], { type: "application/octet-stream", }), }, ]), ); }, }; ``` This is the result: ```json [ { "name": "somatosensory.pdf", "mimeType": "application/pdf", "format": "markdown", "tokens": 0, "data": "# somatosensory.pdf\n## Metadata\n- PDFFormatVersion=1.4\n- IsLinearized=false\n- IsAcroFormPresent=false\n- IsXFAPresent=false\n- IsCollectionPresent=false\n- IsSignaturesPresent=false\n- Producer=Prince 20150210 (www.princexml.com)\n- Title=Anatomy of the Somatosensory System\n\n## Contents\n### Page 1\nThis is a sample document to showcase..." }, { "name": "cat.jpeg", "mimeType": "image/jpeg", "format": "markdown", "tokens": 0, "data": "The image is a close-up photograph of Grumpy Cat, a cat with a distinctive grumpy expression and piercing blue eyes. The cat has a brown face with a white stripe down its nose, and its ears are pointed upright. Its fur is light brown and darker around the face, with a pink nose and mouth. The cat's eyes are blue and slanted downward, giving it a perpetually grumpy appearance. The background is blurred, but it appears to be a dark brown color. Overall, the image is a humorous and iconic representation of the popular internet meme character, Grumpy Cat. The cat's facial expression and posture convey a sense of displeasure or annoyance, making it a relatable and entertaining image for many people." } ] ``` See [Markdown Conversion](https://edgetunnel-b2h.pages.dev/workers-ai/features/markdown-conversion/) for more information on supported formats, REST API and pricing. Mar 18, 2025 1. ### [npm i agents](https://edgetunnel-b2h.pages.dev/changelog/post/2025-03-18-npm-i-agents/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) ![npm i agents](https://edgetunnel-b2h.pages.dev/_astro/npm-i-agents.CXCpJ1-7.apng) #### `agents-sdk` \-> `agents` Updated 📝 **We've renamed the Agents package to `agents`**! If you've already been building with the Agents SDK, you can update your dependencies to use the new package name, and replace references to `agents-sdk` with `agents`: ```sh # Install the new package npm i agents ``` ```sh # Remove the old (deprecated) package npm uninstall agents-sdk # Find instances of the old package name in your codebase grep -r 'agents-sdk' . # Replace instances of the old package name with the new one # (or use find-replace in your editor) sed -i 's/agents-sdk/agents/g' $(grep -rl 'agents-sdk' .) ``` All future updates will be pushed to the new `agents` package, and the older package has been marked as deprecated. #### Agents SDK updates New We've added a number of big new features to the Agents SDK over the past few weeks, including: * You can now set `cors: true` when using `routeAgentRequest` to return permissive default CORS headers to Agent responses. * The regular client now syncs state on the agent (just like the React version). * `useAgentChat` bug fixes for passing headers/credentials, including properly clearing cache on unmount. * Experimental `/schedule` module with a prompt/schema for adding scheduling to your app (with evals!). * Changed the internal `zod` schema to be compatible with the limitations of Google's Gemini models by removing the discriminated union, allowing you to use Gemini models with the scheduling API. We've also fixed a number of bugs with state synchronization and the React hooks. * [ JavaScript ](#tab-panel-3726) * [ TypeScript ](#tab-panel-3727) **JavaScript** ```js // via https://github.com/cloudflare/agents/tree/main/examples/cross-domain export default { async fetch(request, env) { return ( // Set { cors: true } to enable CORS headers. (await routeAgentRequest(request, env, { cors: true })) || new Response("Not found", { status: 404 }) ); }, }; ``` **TypeScript** ```ts // via https://github.com/cloudflare/agents/tree/main/examples/cross-domain export default { async fetch(request: Request, env: Env) { return ( // Set { cors: true } to enable CORS headers. (await routeAgentRequest(request, env, { cors: true })) || new Response("Not found", { status: 404 }) ); }, } satisfies ExportedHandler; ``` #### Call Agent methods from your client code New We've added a new [@unstable\_callable()](https://edgetunnel-b2h.pages.dev/agents/runtime/agents-api/) decorator for defining methods that can be called directly from clients. This allows you call methods from within your client code: you can call methods (with arguments) and get native JavaScript objects back. * [ JavaScript ](#tab-panel-3728) * [ TypeScript ](#tab-panel-3729) **JavaScript** ```js // server.ts import { unstable_callable, Agent } from "agents"; export class Rpc extends Agent { // Use the decorator to define a callable method @unstable_callable({ description: "rpc test", }) async getHistory() { return this.sql`SELECT * FROM history ORDER BY created_at DESC LIMIT 10`; } } ``` **TypeScript** ```ts // server.ts import { unstable_callable, Agent, type StreamingResponse } from "agents"; import type { Env } from "../server"; export class Rpc extends Agent { // Use the decorator to define a callable method @unstable_callable({ description: "rpc test", }) async getHistory() { return this.sql`SELECT * FROM history ORDER BY created_at DESC LIMIT 10`; } } ``` #### agents-starter Updated We've fixed a number of small bugs in the [agents-starter ↗](https://github.com/cloudflare/agents-starter) project — a real-time, chat-based example application with tool-calling & human-in-the-loop built using the Agents SDK. The starter has also been upgraded to use the latest [wrangler v4](https://edgetunnel-b2h.pages.dev/changelog/2025-03-13-wrangler-v4/) release. If you're new to Agents, you can install and run the `agents-starter` project in two commands: ```sh # Install it $ npm create cloudflare@latest agents-starter -- --template="cloudflare/agents-starter" # Run it $ npm run start ``` You can use the starter as a template for your own Agents projects: open up `src/server.ts` and `src/client.tsx` to see how the Agents SDK is used. #### More documentation Updated We've heard your feedback on the Agents SDK documentation, and we're shipping more API reference material and usage examples, including: * Expanded [API reference documentation](https://edgetunnel-b2h.pages.dev/agents/runtime/), covering the methods and properties exposed by the Agents SDK, as well as more usage examples. * More [Client API](https://edgetunnel-b2h.pages.dev/agents/runtime/agents-api/#client-api) documentation that documents `useAgent`, `useAgentChat` and the new `@unstable_callable` RPC decorator exposed by the SDK. * New documentation on how to [route requests to agents](https://edgetunnel-b2h.pages.dev/agents/runtime/communication/routing/) and (optionally) authenticate clients before they connect to your Agents. Note that the Agents SDK is continually growing: the type definitions included in the SDK will always include the latest APIs exposed by the `agents` package. If you're still wondering what Agents are, [read our blog on building AI Agents on Cloudflare ↗](https://blog.cloudflare.com/build-ai-agents-on-cloudflare/) and/or visit the [Agents documentation](https://edgetunnel-b2h.pages.dev/agents/) to learn more. Mar 17, 2025 1. ### [New models in Workers AI](https://edgetunnel-b2h.pages.dev/changelog/post/2025-03-17-new-workers-ai-models/) [ Workers AI ](https://edgetunnel-b2h.pages.dev/workers-ai/) Workers AI is excited to add 4 new models to the catalog, including 2 brand new classes of models with a text-to-speech and reranker model. Introducing: * [@cf/baai/bge-m3](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-m3/) \- a multi-lingual embeddings model that supports over 100 languages. It can also simultaneously perform dense retrieval, multi-vector retrieval, and sparse retrieval, with the ability to process inputs of different granularities. * [@cf/baai/bge-reranker-base](https://edgetunnel-b2h.pages.dev/workers-ai/models/bge-reranker-base/) \- our first reranker model! Rerankers are a type of text classification model that takes a query and context, and outputs a similarity score between the two. When used in RAG systems, you can use a reranker after the initial vector search to find the most relevant documents to return to a user by reranking the outputs. * [@cf/openai/whisper-large-v3-turbo](https://edgetunnel-b2h.pages.dev/workers-ai/models/whisper-large-v3-turbo/) \- a faster, more accurate speech-to-text model. This model was added earlier but is graduating out of beta with pricing included today. * [@cf/myshell-ai/melotts](https://edgetunnel-b2h.pages.dev/workers-ai/models/melotts/) \- our first text-to-speech model that allows users to generate an MP3 with voice audio from inputted text. Pricing is available for each of these models on the [Workers AI pricing page](https://edgetunnel-b2h.pages.dev/workers-ai/platform/pricing/). This docs update includes a few minor bug fixes to the model schema for llama-guard, llama-3.2-1b, which you can review on the [product changelog](https://edgetunnel-b2h.pages.dev/workers-ai/changelog/). Try it out and let us know what you think! Stay tuned for more models in the coming days. Feb 27, 2025 1. ### [New REST API is in open beta!](https://edgetunnel-b2h.pages.dev/changelog/post/2025-02-27-br-rest-api-beta/) [ Browser Run ](https://edgetunnel-b2h.pages.dev/browser-run/) We've released a new REST API for [Browser Rendering](https://edgetunnel-b2h.pages.dev/browser-run/) in open beta, making interacting with browsers easier than ever. This new API provides endpoints for common browser actions, with more to be added in the future. With the **REST API** you can: * **Capture screenshots** – Use `/screenshot` to take a screenshot of a webpage from provided URL or HTML. * **Generate PDFs** – Use `/pdf` to convert web pages into PDFs. * **Extract HTML content** – Use `/content` to retrieve the full HTML from a page. **Snapshot (HTML + Screenshot)** – Use `/snapshot` to capture both the page's HTML and a screenshot in one request * **Scrape Web Elements** – Use `/scrape` to extract specific elements from a page. For example, to capture a screenshot: **Screenshot example** ```bash curl -X POST 'https://api.cloudflare.com/client/v4/accounts//browser-rendering/screenshot' \ -H 'Authorization: Bearer ' \ -H 'Content-Type: application/json' \ -d '{ "html": "Hello World!", "screenshotOptions": { "type": "webp", "omitBackground": true } }' \ --output "screenshot.webp" ``` Learn more in our [documentation](https://edgetunnel-b2h.pages.dev/browser-run/quick-actions/). Feb 26, 2025 1. ### [Introducing Guardrails in AI Gateway](https://edgetunnel-b2h.pages.dev/changelog/post/2025-02-26-guardrails/) [ AI Gateway ](https://edgetunnel-b2h.pages.dev/ai-gateway/) [AI Gateway](https://edgetunnel-b2h.pages.dev/ai-gateway/) now includes [Guardrails](https://edgetunnel-b2h.pages.dev/ai-gateway/features/guardrails/), to help you monitor your AI apps for harmful or inappropriate content and deploy safely. Within the AI Gateway settings, you can configure: * **Guardrails**: Enable or disable content moderation as needed. * **Evaluation scope**: Select whether to moderate user prompts, model responses, or both. * **Hazard categories**: Specify which categories to monitor and determine whether detected inappropriate content should be blocked or flagged. ![Guardrails in AI Gateway](https://edgetunnel-b2h.pages.dev/_astro/Guardrails.BTNc0qeC_Z1HC20z.webp) Learn more in the [blog ↗](https://blog.cloudflare.com/guardrails-in-ai-gateway/) or our [documentation](https://edgetunnel-b2h.pages.dev/ai-gateway/features/guardrails/). Feb 25, 2025 1. ### [Introducing the Agents SDK](https://edgetunnel-b2h.pages.dev/changelog/post/2025-02-25-agents-sdk/) [ Agents ](https://edgetunnel-b2h.pages.dev/agents/)[ Workers ](https://edgetunnel-b2h.pages.dev/workers/) We've released the [Agents SDK ↗](http://blog.cloudflare.com/build-ai-agents-on-cloudflare/), a package and set of tools that help you build and ship AI Agents. You can get up and running with a [chat-based AI Agent ↗](https://github.com/cloudflare/agents-starter) (and deploy it to Workers) that uses the Agents SDK, tool calling, and state syncing with a React-based front-end by running the following command: ```sh npm create cloudflare@latest agents-starter -- --template="cloudflare/agents-starter" # open up README.md and follow the instructions ``` You can also add an Agent to any existing Workers application by installing the `agents` package directly ```sh npm i agents ``` ... and then define your first Agent: **TypeScript** ```ts import { Agent } from "agents"; export class YourAgent extends Agent { // Build it out // Access state on this.state or query the Agent's database via this.sql // Handle WebSocket events with onConnect and onMessage // Run tasks on a schedule with this.schedule // Call AI models // ... and/or call other Agents. } ``` Head over to the [Agents documentation](https://edgetunnel-b2h.pages.dev/agents/) to learn more about the Agents SDK, the SDK APIs, as well as how to test and deploying agents to production. ```json {"@context":"https://schema.org","@type":"BlogPosting","@id":"https://edgetunnel-b2h.pages.dev/changelog/product-group/ai/5/#page","headline":"AI Changelog | Cloudflare Docs","url":"https://edgetunnel-b2h.pages.dev/changelog/product-group/ai/5/","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/"}} ```