--- title: AI Changelog image: https://developers.cloudflare.com/og-changelog.png --- [Skip to content](#main-content) All products Product groups AI Analytics Application performance Application security Cloudflare One Consumer services Core platform Developer platform Docs collections Media Network security Privacy Storage Products 1.1.1.1 (DNS Resolver) Access Agent Lee Agents AI Crawl Control AI Gateway AI Search Analytics API Shield Artifacts Audit Logs Automatic Platform Optimization Basin Basin Catalog Basin Pipelines Basin SQL Billing Bots Browser Isolation Browser Run Cache / CDN CASB Cloudflare CLI Cloudflare for SaaS Cloudflare Fundamentals Cloudflare Images Cloudflare Mesh Cloudflare Network Firewall Cloudflare One Cloudflare One Appliance Cloudflare One Client Cloudflare Tunnel Cloudflare Tunnel for SASE Cloudflare WAN Cloudflare Web Analytics Containers D1 Data Localization Suite Data Loss Prevention Digital Experience Monitoring DNS Durable Objects Email security Email Service Flagship Gateway Go SDK Hyperdrive KV Load Balancing Log Explorer Logpush Logpush Connectors Logs Magic Transit Monetization Gateway Multi-Cloud Networking Network Flow Network Interconnect Organizations Pages Privacy Proxy Queues R2 Radar Realtime Registrar Resource Tagging Risk Score Rules Sandboxes SDK Secrets Store Security Center Security Overview Speed SSL/TLS Stream Support Terraform Turnstile Vectorize WAF Web Search API Workers Workers AI Workers Analytics Engine Workers for Platforms Workers VPC Workflows Zaraz No products found. [View RSS feeds](https://developers.cloudflare.com/fundamentals/new-features/available-rss-feeds/) [ Subscribe to RSS](https://developers.cloudflare.com/changelog/rss/index.xml) Feb 26, 2025 [

Introducing Guardrails in AI Gateway

](https://developers.cloudflare.com/changelog/post/2025-02-26-guardrails/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) now includes [Guardrails](https://developers.cloudflare.com/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://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=2524,height=444,format=webp/_astro/Guardrails.BTNc0qeC.png) Learn more in the [blog ↗︎](https://blog.cloudflare.com/guardrails-in-ai-gateway/) or our [documentation](https://developers.cloudflare.com/ai-gateway/features/guardrails/). Feb 25, 2025 [

Introducing the Agents SDK

](https://developers.cloudflare.com/changelog/post/2025-02-25-agents-sdk/) [Agents](https://developers.cloudflare.com/agents/) [Workers](https://developers.cloudflare.com/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: ```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://developers.cloudflare.com/agents/) to learn more about the Agents SDK, the SDK APIs, as well as how to test and deploying agents to production. Feb 25, 2025 [

Workers AI now supports structured JSON outputs.

](https://developers.cloudflare.com/changelog/post/2025-02-25-json-mode/) [Workers AI](https://developers.cloudflare.com/workers-ai/) Workers AI now supports structured JSON outputs with [JSON mode](https://developers.cloudflare.com/workers-ai/features/json-mode/), which allows you to request a structured output response when interacting with AI models. This makes it much easier to retrieve structured data from your AI models, and avoids the (error prone!) need to parse large unstructured text responses to extract your data. JSON mode in Workers AI is compatible with the OpenAI SDK's [structured outputs ↗︎](https://platform.openai.com/docs/guides/structured-outputs) `response_format` API, which can be used directly in a Worker: ```js import { OpenAI } from "openai"; // Define your JSON schema for a calendar event const CalendarEventSchema = { type: "object", properties: { name: { type: "string" }, date: { type: "string" }, participants: { type: "array", items: { type: "string" } }, }, required: ["name", "date", "participants"], }; export default { async fetch(request, env) { const client = new OpenAI({ apiKey: env.OPENAI_API_KEY, // Optional: use AI Gateway to bring logs, evals & caching to your AI requests // https://developers.cloudflare.com/ai-gateway/usage/providers/openai/ // baseUrl: "https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/openai" }); const response = await client.chat.completions.create({ model: "gpt-4o-2024-08-06", messages: [ { role: "system", content: "Extract the event information." }, { role: "user", content: "Alice and Bob are going to a science fair on Friday.", }, ], // Use the `response_format` option to request a structured JSON output response_format: { // Set json_schema and provide ra schema, or json_object and parse it yourself type: "json_schema", schema: CalendarEventSchema, // provide a schema }, }); // This will be of type CalendarEventSchema const event = response.choices[0].message.parsed; return Response.json({ calendar_event: event, }); }, }; ``` ```ts import { OpenAI } from "openai"; interface Env { OPENAI_API_KEY: string; } // Define your JSON schema for a calendar event const CalendarEventSchema = { type: "object", properties: { name: { type: "string" }, date: { type: "string" }, participants: { type: "array", items: { type: "string" } }, }, required: ["name", "date", "participants"], }; export default { async fetch(request: Request, env: Env) { const client = new OpenAI({ apiKey: env.OPENAI_API_KEY, // Optional: use AI Gateway to bring logs, evals & caching to your AI requests // https://developers.cloudflare.com/ai-gateway/usage/providers/openai/ // baseUrl: "https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/openai" }); const response = await client.chat.completions.create({ model: "gpt-4o-2024-08-06", messages: [ { role: "system", content: "Extract the event information." }, { role: "user", content: "Alice and Bob are going to a science fair on Friday.", }, ], // Use the `response_format` option to request a structured JSON output response_format: { // Set json_schema and provide ra schema, or json_object and parse it yourself type: "json_schema", schema: CalendarEventSchema, // provide a schema }, }); // This will be of type CalendarEventSchema const event = response.choices[0].message.parsed; return Response.json({ calendar_event: event, }); }, }; ``` To learn more about JSON mode and structured outputs, visit the [Workers AI documentation](https://developers.cloudflare.com/workers-ai/features/json-mode/). Feb 24, 2025 [

Workers AI larger context windows

](https://developers.cloudflare.com/changelog/post/2025-02-24-context-windows/) [Workers AI](https://developers.cloudflare.com/workers-ai/) We've updated the Workers AI text generation models to include context windows and limits definitions and changed our APIs to estimate and validate the number of tokens in the input prompt, not the number of characters. This update allows developers to use larger context windows when interacting with Workers AI models, which can lead to better and more accurate results. Our [catalog page](https://developers.cloudflare.com/workers-ai/models/) provides more information about each model's supported context window. Feb 20, 2025 [

Workers AI updated pricing

](https://developers.cloudflare.com/changelog/post/2025-02-20-updated-pricing-docs/) [Workers AI](https://developers.cloudflare.com/workers-ai/) We've updated the Workers AI [pricing](https://developers.cloudflare.com/workers-ai/platform/pricing/) to include the latest models and how model usage maps to Neurons. - Each model's core input format(s) (tokens, audio seconds, images, etc) now include mappings to Neurons, making it easier to understand how your included Neuron volume is consumed and how you are charged at scale - Per-model pricing, instead of the previous bucket approach, allows us to be more flexible on how models are charged based on their size, performance and capabilities. As we optimize each model, we can then pass on savings for that model. - You will still only pay for what you consume: Workers AI inference is serverless, and not billed by the hour. Going forward, models will be launched with their associated Neuron costs, and we'll be updating the Workers AI dashboard and API to reflect consumption in both raw units and Neurons. Visit the [Workers AI pricing](https://developers.cloudflare.com/workers-ai/platform/pricing/) page to learn more about Workers AI pricing. Feb 14, 2025 [

Build AI Agents with Example Prompts

](https://developers.cloudflare.com/changelog/post/2025-02-14-example-ai-prompts/) [Agents](https://developers.cloudflare.com/agents/) [Workers](https://developers.cloudflare.com/workers/) [Workflows](https://developers.cloudflare.com/workflows/) We've added an [example prompt](https://developers.cloudflare.com/workers/get-started/prompting/) to help you get started with building AI agents and applications on Cloudflare [Workers](https://developers.cloudflare.com/workers/), including [Workflows](https://developers.cloudflare.com/workflows/), [Durable Objects](https://developers.cloudflare.com/durable-objects/), and [Workers KV](https://developers.cloudflare.com/kv/). You can use this prompt with your favorite AI model, including Claude 3.5 Sonnet, OpenAI's o3-mini, Gemini 2.0 Flash, or Llama 3.3 on Workers AI. Models with large context windows will allow you to paste the prompt directly: provide your own prompt within the `` tags. ```sh {paste_prompt_here} user: Build an AI agent using Cloudflare Workflows. The Workflow should run when a new GitHub issue is opened on a specific project with the label 'help' or 'bug', and attempt to help the user troubleshoot the issue by calling the OpenAI API with the issue title and description, and a clear, structured prompt that asks the model to suggest 1-3 possible solutions to the issue. Any code snippets should be formatted in Markdown code blocks. Documentation and sources should be referenced at the bottom of the response. The agent should then post the response to the GitHub issue. The agent should run as the provided GitHub bot account. ``` This prompt is still experimental, but we encourage you to try it out and [provide feedback ↗︎](https://github.com/cloudflare/cloudflare-docs/issues/new?template=content.edit.yml). Feb 6, 2025 [

Request timeouts and retries with AI Gateway

](https://developers.cloudflare.com/changelog/post/2025-02-05-aig-request-handling/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) AI Gateway adds additional ways to handle requests - [Request Timeouts](https://developers.cloudflare.com/ai-gateway/configuration/request-handling/#request-timeouts) and [Request Retries](https://developers.cloudflare.com/ai-gateway/configuration/request-handling/#request-retries), making it easier to keep your applications responsive and reliable. Timeouts and retries can be used on both the [Universal Endpoint](https://developers.cloudflare.com/ai-gateway/usage/universal/) or directly to a [supported provider](https://developers.cloudflare.com/ai-gateway/usage/providers/). **Request timeouts** A [request timeout](https://developers.cloudflare.com/ai-gateway/configuration/request-handling/#request-timeouts) allows you to trigger [fallbacks](https://developers.cloudflare.com/ai-gateway/configuration/fallbacks/) or a retry if a provider takes too long to respond. To set a request timeout directly to a provider, add a `cf-aig-request-timeout` header. *Provider-specific endpoint examplebash* ```bash curl https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/workers-ai/@cf/meta/llama-3.1-8b-instruct \ --header 'Authorization: Bearer {cf_api_token}' \ --header 'Content-Type: application/json' \ --header 'cf-aig-request-timeout: 5000' --data '{"prompt": "What is Cloudflare?"}' ``` **Request retries** A [request retry](https://developers.cloudflare.com/ai-gateway/configuration/request-handling/#request-retries) automatically retries failed requests, so you can recover from temporary issues without intervening. To set up request retries directly to a provider, add the following headers: - cf-aig-max-attempts (number) - cf-aig-retry-delay (number) - cf-aig-backoff ("constant" | "linear" | "exponential) Feb 5, 2025 [

AI Gateway adds Cerebras, ElevenLabs, and Cartesia as new providers

](https://developers.cloudflare.com/changelog/post/2025-02-04-aig-provider-cartesia-eleven-cerebras/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) has added three new providers: [Cartesia](https://developers.cloudflare.com/ai-gateway/usage/providers/cartesia/), [Cerebras](https://developers.cloudflare.com/ai-gateway/usage/providers/cerebras/), and [ElevenLabs](https://developers.cloudflare.com/ai-gateway/usage/providers/elevenlabs/), giving you more even more options for providers you can use through AI Gateway. Here's a brief overview of each: - [Cartesia](https://developers.cloudflare.com/ai-gateway/usage/providers/cartesia/) provides text-to-speech models that produce natural-sounding speech with low latency. - [Cerebras](https://developers.cloudflare.com/ai-gateway/usage/providers/cerebras/) delivers low-latency AI inference to Meta's Llama 3.1 8B and Llama 3.3 70B models. - [ElevenLabs](https://developers.cloudflare.com/ai-gateway/usage/providers/elevenlabs/) offers text-to-speech models with human-like voices in 32 languages. ![Example of Cerebras log in AI Gateway](https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=2278,height=1020,format=webp/_astro/cerebras2.qHYP0ZnF.png) To get started with AI Gateway, just update the base URL. Here's how you can send a request to [Cerebras](https://developers.cloudflare.com/ai-gateway/usage/providers/cerebras/) using cURL: *Example fetch requestbash* ```bash curl -X POST https://gateway.ai.cloudflare.com/v1/ACCOUNT_TAG/GATEWAY/cerebras/chat/completions \ --header 'content-type: application/json' \ --header 'Authorization: Bearer CEREBRAS_TOKEN' \ --data '{ "model": "llama-3.3-70b", "messages": [ { "role": "user", "content": "What is Cloudflare?" } ] }' ``` Jan 30, 2025 [

AI Gateway Introduces New Worker Binding Methods

](https://developers.cloudflare.com/changelog/post/2025-01-26-worker-binding-methods/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) We have released new [Workers bindings API methods](https://developers.cloudflare.com/ai-gateway/usage/worker-binding-methods/), allowing you to connect Workers applications to AI Gateway directly. These methods simplify how Workers calls AI services behind your AI Gateway configurations, removing the need to use the REST API and manually authenticate. To add an AI binding to your Worker, include the following in your [Wrangler configuration file](https://developers.cloudflare.com/workers/wrangler/configuration/): ![Add an AI binding to your Worker.](https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=754,height=135,format=webp/_astro/add-binding.BoYTiyon.png) With the new AI Gateway binding methods, you can now: - Send feedback and update metadata with `patchLog`. - Retrieve detailed log information using `getLog`. - Execute [universal requests](https://developers.cloudflare.com/ai-gateway/usage/universal/) to any AI Gateway provider with `run`. For example, to send feedback and update metadata using `patchLog`: ![Send feedback and update metadata using patchLog:](https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=736,height=235,format=webp/_astro/send-feedback.BGRzKmd9.png) Jan 30, 2025 [

Increased Browser Rendering limits!

](https://developers.cloudflare.com/changelog/post/2025-01-30-browser-rendering-more-instances/) [Workers](https://developers.cloudflare.com/workers/) [Browser Run](https://developers.cloudflare.com/browser-run/) [Browser Rendering](https://developers.cloudflare.com/browser-run/) now supports 10 concurrent browser instances per account *and* 10 new instances per minute, up from the previous limits of 2. This allows you to launch more browser tasks from [Cloudflare Workers](https://developers.cloudflare.com/workers). To manage concurrent browser sessions, you can use [Queues](https://developers.cloudflare.com/queues/) or [Workflows](https://developers.cloudflare.com/workflows/): *index.jsjs* ```js export default { async queue(batch, env) { for (const message of batch.messages) { const browser = await puppeteer.launch(env.BROWSER); const page = await browser.newPage(); try { await page.goto(message.url, { waitUntil: message.waitUntil, }); // Process page... } finally { await browser.close(); } } }, }; ``` *index.tsts* ```ts interface QueueMessage { url: string; waitUntil: number; } export interface Env { BROWSER_QUEUE: Queue; BROWSER: Fetcher; } export default { async queue(batch: MessageBatch, env: Env): Promise { for (const message of batch.messages) { const browser = await puppeteer.launch(env.BROWSER); const page = await browser.newPage(); try { await page.goto(message.url, { waitUntil: message.waitUntil, }); // Process page... } finally { await browser.close(); } } }, }; ``` Jan 2, 2025 [

AI Gateway adds DeepSeek as a Provider

](https://developers.cloudflare.com/changelog/post/2025-01-07-aig-provider-deepseek/) [AI Gateway](https://developers.cloudflare.com/ai-gateway/) [**AI Gateway**](https://developers.cloudflare.com/ai-gateway/) now supports [**DeepSeek**](https://developers.cloudflare.com/ai-gateway/usage/providers/deepseek/), including their cutting-edge DeepSeek-V3 model. With this addition, you have even more flexibility to manage and optimize your AI workloads using AI Gateway. Whether you're leveraging DeepSeek or other providers, like OpenAI, Anthropic, or [Workers AI](https://developers.cloudflare.com/workers-ai/), AI Gateway empowers you to: - **Monitor**: Gain actionable insights with analytics and logs. - **Control**: Implement caching, rate limiting, and fallbacks. - **Optimize**: Improve performance with feedback and evaluations. ![AI Gateway adds DeepSeek as a provider](https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=1600,height=131,format=webp/_astro/deepseek.hirkr3rv.png) To get started, simply update the base URL of your DeepSeek API calls to route through AI Gateway. Here's how you can send a request using cURL: *Example fetch requestbash* ```bash curl https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/deepseek/chat/completions \ --header 'content-type: application/json' \ --header 'Authorization: Bearer DEEPSEEK_TOKEN' \ --data '{ "model": "deepseek-chat", "messages": [ { "role": "user", "content": "What is Cloudflare?" } ] }' ``` For detailed setup instructions, see our [DeepSeek provider documentation](https://developers.cloudflare.com/ai-gateway/usage/providers/deepseek/). Sep 23, 2024 [

AI Crawl Control

](https://developers.cloudflare.com/changelog/post/2024-09-23-ai-audit-launch/) [AI Crawl Control](https://developers.cloudflare.com/ai-crawl-control/) Every site on Cloudflare now has access to [**AI Audit**](https://developers.cloudflare.com/ai-crawl-control/), which summarizes the crawling behavior of popular and known AI services. You can use this data to: - Understand how and how often crawlers access your site (and which content is the most popular). - Block specific AI bots accessing your site. - Use Cloudflare to enforce your `robots.txt` policy via an automatic WAF rule. ![View AI bot activity with AI Audit](https://developers.cloudflare.com/cdn-cgi/image/onerror=redirect,width=1494,height=746,format=webp/_astro/ai-crawl-control-overview.Dr_yGKOC.png) To get started, explore [AI audit](https://developers.cloudflare.com/ai-crawl-control/). ```json {"@context":"https://schema.org","@type":"BlogPosting","@id":"https://developers.cloudflare.com/changelog/product-group/ai/8/#page","headline":"AI Changelog","url":"https://developers.cloudflare.com/changelog/product-group/ai/8/","inLanguage":"en","image":"https://developers.cloudflare.com/og-changelog.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}} ```