<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>New API on Margrop Blog</title>
		<link>https://blog.margrop.net/en/tag/new-api/</link>
		<description>Recent content in New API on Margrop Blog</description>
		<generator>Hugo</generator>
		<language>en-US</language>
		
		
		
		
			<lastBuildDate>Fri, 10 Jul 2026 15:30:00 +0800</lastBuildDate>
		
			<atom:link href="https://blog.margrop.net/en/tag/new-api/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Stop Sprinkling API Keys Everywhere: My Self-Hosted NewAPI Relay Station</title>
				<link>https://blog.margrop.net/en/post/newapi-self-hosted-relay-station/</link>
				<pubDate>Fri, 10 Jul 2026 15:30:00 +0800</pubDate>
				<guid>https://blog.margrop.net/en/post/newapi-self-hosted-relay-station/</guid>
				<description>&lt;blockquote&gt;&#xA;&lt;p&gt;&lt;strong&gt;TL;DR&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;NewAPI is not a free-model trick and it is not a mysterious proxy. In my setup, it is the front desk for AI usage: every app talks to one endpoint, while the gateway routes requests to authorized upstream providers and handles tokens, quotas, groups, model limits, logs, and usage accounting. For a personal deployment, the big win is not “one more dashboard”; it is no longer scattering upstream keys across every client, script, and agent.&lt;/p&gt;&#xA;&lt;p&gt;This post explains why I wanted a self-hosted model relay, what people usually misunderstand, how to deploy a minimal Docker Compose version, why I add persistent storage, and how to use one-click scripts for Windows 11, Ubuntu 26.04, and macOS 26. It also includes an agent-driven setup prompt with strict boundaries. No private address, complete machine name, private domain, or real secret is included.&lt;/p&gt;&#xA;&lt;/blockquote&gt;</description>
			</item>
	</channel>
</rss>
