Cloudflare Launches Platform to Deploy Fast, Secure, Compliant AI Inference at Scale


Cloudflare introduces Workers AI for end-to-end infrastructure needed to scale and deploy AI models efficiently and affordably for the next era of AI applications.

Cloudflare, Inc., the leading connectivity cloud company, announced that developers can now build full-stack AI applications on Cloudflare’s network. Cloudflare’s developer platform will provide the best end-to-end experience for developers building AI applications, enabling fast and affordable inference without the need to manage infrastructure. As every business, from startups to enterprises, looks to augment their services with artificial intelligence, Cloudflare’s platform is empowering developers with the velocity to ship a production-ready application quickly, with security, compliance, and speed built in.

Business leaders – from Fortune 1000 companies looking to augment their services with AI, to AI startups on a mission to build the next culture-defining application – want to ship production-scale AI-powered applications. Organisations are trying to move quickly to realise value fast. However, they face challenges like rapidly ballooning and opaque costs to deploy AI and ensuring customer data remains private and in compliance with regulations. Developers are facing a slew of new vendors, requiring them to understand new tools quickly and connect many complex, disparate services together. C-level business leaders are looking to optimise costs amid expensive technology, tools, and staffing.

“Cloudflare has all the infrastructure developers need to build scalable AI-powered applications, and can now provide AI inference as close to the user as possible. We’re investing to make it easy for every developer to have access to powerful, affordable tools to build the future,” said Matthew Prince, CEO and Co-founder of Cloudflare. “Workers AI will empower developers to build production-ready AI experiences efficiently and affordably, and in days, instead of what typically takes entire teams weeks or even months.”

“As enterprises look to maximise their operational velocity, more and more of them are turning to artificial intelligence,” said Stephen O’Grady, Principal Analyst with RedMonk. “But it’s critical to deliver a quality developer experience around AI, with abstractions to simplify the interfaces and controls to monitor costs. This is precisely what Cloudflare has optimised its Workers platform for.”

Introducing Workers AI: Industry’s First Serverless AI at Scale

Today, Workers AI is delivering a simple, affordable way for developers to run AI models on Cloudflare’s global network. Through significant partnerships, Cloudflare will now provide access to GPUs running on Cloudflare’s massive global network to ensure AI inference can happen close to users for a low-latency end-user experience. When combined with our Data Localization Suite to help control where data is inspected, Workers AI will also help customers anticipate potential compliance and regulatory requirements that are likely to arise as governments create policies around AI use. Cloudflare’s privacy-first approach to application development can help companies keep their promises to their customers by ensuring data used for inference is not used for training LLMs. Cloudflare currently supports a model catalogue to help developers get started quickly, with use cases including LLM, speech-to-text, image classification, sentiment analysis and more.

Introducing Vectorize: A Vector Database That Speeds Up Your AI Workflows

Cloudflare’s new vector database, Vectorize, enables developers to build full-stack AI applications entirely on Cloudflare, from generating your embeddings with the built-in models in Workers AI and indexing them in Vectorize to querying them and storing source data in R2. With Workers AI and Vectorize, developers no longer have to glue multiple pieces together to empower their apps with AI and machine learning – they can do it all on one platform.

Vectorize also benefits from Cloudflare’s global network, allowing vector queries to happen closer to users, reducing latency and overall inference time. It also integrates with the wider AI ecosystem, allowing developers to store embeddings generated with OpenAI and Cohere, so that teams can bring embeddings they already have and still benefit from Vectorize when it comes to scaling AI apps to production.

Introducing AI Gateway: Observability and Scale for AI

Today, Cloudflare is introducing AI Gateway to make AI applications more reliable, observable, and scalable. According to the latest forecasts from IDC, AI spending is expected to balloon to $154 billion this year and increase to more than $300 billion in 2026. However, developers and C-suite leaders have no way of understanding how money is being spent across AI infrastructure or how many and from where queries are happening.

Developers should be able to focus on what they’re building, not the infrastructure, scaling, costs, or observability pieces behind it. AI Gateway will give developers observability features to understand AI traffic, like the number of requests, number of users, cost of running the app, and duration of requests. Additionally, developers can manage costs with caching and rate limiting. With caching, customers will be able to cache answers across repeated questions, reducing the need to constantly make multiple calls to expensive APIs. Rate limiting will help to manage the malicious actors and heavy traffic in order to manage growth and costs, giving developers more control over how they scale their applications.