Access LLMs for Free: A Guide to Cloudflare's Services | Worker AI | AI Gateway
How to call hosted LLMs through Cloudflare Workers AI and AI Gateway without paying for API keys while you learn and prototype.
Videos
From my YouTube channel: building AI applications with Java, running LLMs locally and on Cloudflare, Kubernetes troubleshooting, and the Java platform features I rely on. Videos load only when you press play.
An end to end LLM application: a Java Spring Boot service calling Cloudflare Workers AI, with MongoDB holding the conversation and document data.
How to call hosted LLMs through Cloudflare Workers AI and AI Gateway without paying for API keys while you learn and prototype.
Running large language models on your own machine: what hardware actually matters, and which tools make it painless.
Port forwarding as a debugging tool for microservices on Kubernetes, with the tips and traps that come with it.
What arrived in OpenJDK 15 and why it mattered for Java developers moving off older releases.
Locality sensitive hashing explained: finding near-duplicate items fast, and where the technique shows up in real systems.
Switch expressions became standard in Java 14 under JEP 361. This talk walks through the syntax and the bugs it prevents.