<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
        xmlns:news="http://www.google.com/schemas/sitemap-news/0.9">
  <url>
    <loc>https://tokencost.app/blog/openai-agents-api-hosted-sandbox-pricing</loc>
    <news:news>
      <news:publication>
        <news:name>TokenCost</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-09-13T00:00:00.000Z</news:publication_date>
      <news:title>OpenAI says the Agents API has no additional fees, and it does not. The sandbox every hosted session runs in bills at a container card whose rates have not moved since March, on a memory tier you cannot pick and a clock OpenAI has not said when it starts.</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://tokencost.app/blog/sakana-fugu-max-pricing-orchestration-tokens</loc>
    <news:news>
      <news:publication>
        <news:name>TokenCost</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-09-12T00:00:00.000Z</news:publication_date>
      <news:title>Sakana priced Fugu Max at $2 and $6, which is Qwen3.8 Max&apos;s card to the cent, and says the output line is 40% to 60% under Sonnet 5, Terra and Kimi K3. The tokens billed at that rate include every internal call the orchestrator makes, and Sakana publishes neither the count nor the models it calls.</news:title>
    </news:news>
  </url>
</urlset>