Flex Inference: 50% Off LLM Calls on Gemini, OpenAI, and Bedrock
Every major AI provider now offers half-price inference if you can tolerate a few extra seconds of latency. One parameter change. Same API. Here's how it works and why.
testy.cool
Notes on LLMs, agents, automation and development.
Latest posts
UCP - How to Actually Make Money With It
Universal Commerce Protocol lets AI agents buy things. Here's how developers can monetize it and what store owners need to know.
Setting Up SSH for Claude Code
How to configure SSH so Claude Code can run commands on remote servers
Fix Cloudflare Pages Redirect to Custom Domain
Your *.pages.dev URL is ranking in Google instead of your custom domain. Here's how to fix it with a proper 301 redirect.
CSS Clamp Calculator and Tutorial
Stop using breakpoint jumps. This calculator generates fluid CSS values, and the tutorial explains exactly why the math works.
How to Set Up a Blog with Fumadocs
Build a documentation-style blog using Fumadocs and Next.js. Get table of contents, MDX support, and clean typography out of the box.
How to Remove Windows NUL File
That NUL file that appeared while vibe coding? Here's how to delete it.