Cloudflare Accelerates AI App Development with Global, Infinitely Scalable Network

Cloudflare, Inc., the company helping to build a better internet, is introducing a new platform—accompanied by high performance at scale, a new vector database, and observability capabilities—that will enable developers to build full-stack AI applications on Cloudflare’s network. Dubbed Workers AI, this solution offers fast and affordable inference without the need to manage infrastructure, driving increased productivity for shipping out production-ready, fast, and secure applications.

While every company wants to adopt and build AI applications, it is far easier said than done. AI development and deployment requires significant financial investment, on top of its already complex and demanding nature.

Though developers are eager to innovate in this realm, business leaders are set on optimizing costs, tools, and staffing, according to Cloudflare.

The Cloudflare Developer Platform offers development teams with everything they need to deliver seamless, secure applications, backed by Cloudflare’s infinitely scalable global network. The platform is further amplified by three new solutions: Workers AI, Vectorize, and AI Gateway.

Workers AI was created to “give developers all the tools they need to build applications,” said Matthew Prince, CEO of Cloudflare. “Workers AI helps developers run well-known AI models on serverless GPUs, all on Cloudflare’s trusted global network. It integrates seamlessly with our developer platform, but to make it truly accessible, we’ve made it platform agnostic, so it also works everywhere else, made available via a REST API.”

By providing access to GPUs running on Cloudflare’s hyper-distributed edge network, developers are afforded peace of mind that AI inference is happening as close to users as possible, driving low-latency end-user experiences.

Additionally, Workers AI ensures that data remains within the region it resides, allowing users to adhere to potential compliance and regulatory requirements. Cloudflare’s privacy-first approach further drives compliance, guaranteeing that data used for interference will not be released for training.

Cloudflare’s launch of Vectorize, a new vector database, allows developers to build full-stack AI applications entirely on Cloudflare.

“Vector databases are a critical building block when it comes to developers implementing AI into new and existing applications, especially for generative AI, semantic search, and recommendation use-cases (just to name a few). It’s hard to scale up a lot of these use cases into ‘production’ without a vector database,” said Prince. “Being able to experiment and prototype is one thing, but we think a differentiator for us is enabling developers to scale to production (one of the core tenets of Workers itself).”

Vectorize benefits from Cloudflare’s global network, forwarding low latency and inference time. It integrates with the wider AI ecosystem, enabling users to store embeddings generated with OpenAI and Cohere.

Paired with Workers AI, Vectorize allows developers to power AI-enabled apps—that are affordable to operate at scale—within a single platform.

Finally, Cloudflare is unveiling Gateway AI, a means to ensure that AI apps built on Cloudflare are reliable, observable, and scalable. GatewayAI removes the mystery from AI app development by offering visibility into AI traffic, including variables such as number of requests, number of users, cost of running the app, and duration of requests.

Caching and rate limiting also empowers developers to mitigate against growing costs, reducing calls to APIs for repeated queries and helping to manage malicious actors and heavy traffic.

“Cloudflare’s AI announcements make performant and scalable AI technology more accessible to developers looking to launch the next generation of applications,” explained Prince. “We’re able to add this technology to our existing network, allowing us to leverage our existing infrastructure and pass on better performance, as well as better cost. We’re the only provider at this level of scale that lets developers and companies only pay for the compute they use, which is going to open doors to a lot of new developers and organizations that were previously left out of the AI race.”

To learn more about the Cloudflare Developer Platform, as well as its newly released AI capabilities, please visit