<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Agent-Native on Vic Boomer</title>
    <link>https://vicboomer.com/tags/agent-native/</link>
    <description>Recent content in Agent-Native on Vic Boomer</description>
    <generator>Hugo</generator>
    <language>nl</language>
    <lastBuildDate>Sun, 19 Apr 2026 18:45:00 +0200</lastBuildDate>
    <atom:link href="https://vicboomer.com/tags/agent-native/feed.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>De rekening van agent-native</title>
      <link>https://vicboomer.com/nl/essays/de-rekening-van-agent-native/</link>
      <pubDate>Sun, 19 Apr 2026 18:45:00 +0200</pubDate>
      <guid>https://vicboomer.com/nl/essays/de-rekening-van-agent-native/</guid>
      <description>&lt;p&gt;OpenAI verandert vanaf 31 maart 2026 de meeteenheid van zijn agent-containers. Tot dan werden die per memory-tier geprijsd, drie cent per gigabyte. Vanaf 31 maart worden ze geprijsd per sessie van twintig minuten, met een eigen teller naast het model. Google kondigde twee weken eerder project-level spending-caps aan in AI Studio, en handhaaft vanaf 1 april maandlimieten per tier. Gemini biedt daarnaast Flex- en Priority-tiers, prijsvarianten op dezelfde inference-meter. Anthropic rekent web search los van tokens, tegen tien dollar per duizend calls, en laat Managed Agents lopen op tokens én op sessieruntime.&lt;/p&gt;</description>
    </item>
    <item>
      <title>The bill of agent-native</title>
      <link>https://vicboomer.com/essays/en-the-bill-of-agent-native/</link>
      <pubDate>Sun, 19 Apr 2026 18:45:00 +0200</pubDate>
      <guid>https://vicboomer.com/essays/en-the-bill-of-agent-native/</guid>
      <description>&lt;p&gt;As of March 31, 2026, OpenAI is changing the billing unit for its agent containers. Until then they were priced per memory tier, three cents per gigabyte. From March 31 onward they&amp;rsquo;re priced per session of twenty minutes, with their own meter alongside the model. Two weeks earlier, Google introduced project-level spending caps in AI Studio, and enforces monthly per-tier caps from April 1. Gemini also offers Flex and Priority tiers, pricing variants on the same inference meter. Anthropic bills web search separately from tokens, at ten dollars per thousand calls, and runs Managed Agents on both tokens and session runtime.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
