<?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>Openrouter on danilchenko.dev</title><link>https://www.danilchenko.dev/tags/openrouter/</link><description>Recent content in Openrouter on danilchenko.dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 29 Aug 2026 07:32:10 +0000</lastBuildDate><atom:link href="https://www.danilchenko.dev/tags/openrouter/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Food Recognition in Production: What Shipping soba Taught Me</title><link>https://www.danilchenko.dev/posts/food-recognition-llm/</link><pubDate>Sat, 29 Aug 2026 07:32:10 +0000</pubDate><guid>https://www.danilchenko.dev/posts/food-recognition-llm/</guid><description>How I picked an LLM for food photo recognition in soba: a benchmark, a live A/B that cut scan cost to $0.005, and the prompt work that fixes portion weight.</description></item></channel></rss>