MacOS - Tag - Shengxu ยท Cloud Architecture & DevOpshttps://shengxu.pages.dev/en/tags/macos/Cloud architecture & DevOps notes by Shengxu: Kubernetes, Cilium, observability, LLM infra, AI agents.Hugo 0.153.2 & FixIt v0.4.0-alpha.3-20251225101113-8ffb9a95enSat, 14 Feb 2026 10:18:00 +0800Weekend Project: Building a Local Load Balancer for LLM API Keyshttps://shengxu.pages.dev/en/posts/llm-api-load-balancer/Sat, 14 Feb 2026 10:18:00 +0800https://shengxu.pages.dev/en/posts/llm-api-load-balancer/AIDevOpsObservability<p>Lately, because I&rsquo;ve been using various LLM services (OpenAI, Gemini, DeepSeek, etc.) intensively, I&rsquo;ve run into a very real pain point: <strong>being broke</strong>.</p> <p>To save money, I applied for multiple free API keys (like Google Gemini&rsquo;s Free Tier or DeepSeek&rsquo;s complimentary credits), but these free keys often come with strict rate limits (RPM/TPM). Just when I&rsquo;m in the flow writing code, a <code>429 Too Many Requests</code> error pops up, completely breaking my train of thought. It&rsquo;s really frustrating.</p>