<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Gateway on zolty.systems</title><link>https://blog.zolty.systems/tags/gateway/</link><description>Recent content in Gateway on zolty.systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 12 Jun 2026 20:00:00 -0400</lastBuildDate><atom:link href="https://blog.zolty.systems/tags/gateway/index.xml" rel="self" type="application/rss+xml"/><item><title>A LiteLLM gateway for the homelab: one endpoint, many models, hard cost caps</title><link>https://blog.zolty.systems/posts/2026-06-12-litellm-gateway-homelab/</link><pubDate>Fri, 12 Jun 2026 20:00:00 -0400</pubDate><guid>https://blog.zolty.systems/posts/2026-06-12-litellm-gateway-homelab/</guid><description>I route every LLM call — local Ollama, cloud frontier models, OpenRouter — through a single LiteLLM gateway with per-key budgets and spend alerts, so cheap bulk work stays cheap and nothing runs away.</description></item></channel></rss>