<?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>Cost-Optimization on Onur Baydaş</title><link>https://onurbaydas.com/en/tags/cost-optimization/</link><description>Recent content in Cost-Optimization on Onur Baydaş</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 17 Oct 2026 12:15:22 +0300</lastBuildDate><atom:link href="https://onurbaydas.com/en/tags/cost-optimization/index.xml" rel="self" type="application/rss+xml"/><item><title>Open-weight models gain traction at Vercel</title><link>https://onurbaydas.com/en/news/2026-10-17-open-weight-models-vercel-usage/</link><pubDate>Sat, 17 Oct 2026 12:15:22 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-17-open-weight-models-vercel-usage/</guid><description>Open-weight AI models account for 71.5% of tokens processed through the Vercel gateway. These models represent nearly a quarter of estimated spending, indicating growing adoption.</description></item><item><title>Asana Cuts Model Costs 76x in Browser Tests with GPT-6.1 Sol</title><link>https://onurbaydas.com/en/news/2026-10-16-asana-gpt-61-sol-cost-reduction/</link><pubDate>Fri, 16 Oct 2026 00:17:33 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-16-asana-gpt-61-sol-cost-reduction/</guid><description>Asana achieved significant cost and performance improvements in its browser agent tests by using the GPT-6.1 Sol model. This enables them to offer more capable models to their customers at a much lower cost.</description></item></channel></rss>