<?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>成本记账 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E6%88%90%E6%9C%AC%E8%AE%B0%E8%B4%A6/</link><description>Recent content in 成本记账 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 08 Oct 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%88%90%E6%9C%AC%E8%AE%B0%E8%B4%A6/index.xml" rel="self" type="application/rss+xml"/><item><title>用 LiteLLM 把十几家大模型收进一个网关：统一 key、限流与记账</title><link>https://guijiagi.com/posts/2026-10-08-litellm-gateway-proxy/</link><pubDate>Thu, 08 Oct 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-08-litellm-gateway-proxy/</guid><description>团队同时接 OpenAI、DeepSeek、智谱、本地模型时，各自适配是噩梦。LiteLLM 用一套 OpenAI 协议把它们统一成一个入口。</description></item></channel></rss>