
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>MINSSAM.COM</title>
      <link>https://minssam.com/en/blog</link>
      <description>MINSSAM.COM — 민쌤의 생각과 도구 노트</description>
      <language>en-US</language>
      <managingEditor>address@yoursite.com (민쌤 (MINSSAM))</managingEditor>
      <webMaster>address@yoursite.com (민쌤 (MINSSAM))</webMaster>
      <lastBuildDate>Wed, 06 May 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://minssam.com/en/tags/flashlite/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://minssam.com/en/blog/gemini-25-flash-lite-ga-sft-may2026</guid>
    <title>Gemini 2.5 Flash-Lite Goes GA — Faster, 20-30% Cheaper, and Now with SFT Support</title>
    <link>https://minssam.com/en/blog/gemini-25-flash-lite-ga-sft-may2026</link>
    <description>Google launched Gemini 2.5 Flash-Lite to general availability on Vertex AI. It uses 20-30% fewer tokens than the standard Flash while maintaining reasoning, coding, and multimodal performance — and it now supports supervised fine-tuning (SFT). At the same time, Deep Research opened for free on the Flash model, and Native Audio got sharper. A significant update for cost-conscious teams and individuals alike.</description>
    <pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate>
    <author>address@yoursite.com (민쌤 (MINSSAM))</author>
    <category>Gemini</category><category>Gemini25Flash</category><category>FlashLite</category><category>GoogleAI</category><category>VertexAI</category><category>SFT</category><category>NativeAudio</category><category>DeepResearch</category><category>AIProductivity</category><category>LLMCostReduction</category>
  </item>

    </channel>
  </rss>
