{
  "id": "2024-10-21-gemini-context-caching",
  "slug": "gemini-context-caching",
  "title": "Gemini Context Caching",
  "date": "2024-10-21T14:00:00.000Z",
  "categories": [
    "New",
    "AI Models"
  ],
  "url": "https://feedback.typingmind.com/changelog/gemini-context-caching",
  "contentHtml": "<p>Gemini Context Caching is now available on TypingMind! 🔥</p><p>Supported models:</p><ul><li>Gemini 1.5 Pro</li><li>Gemini 1.5 Flash</li></ul><p>The minimum input token count for context caching is 32,768.</p><aside class=\"callout\"><p>Prompt Caching allows users to make repeated API calls more efficiently by reusing context from recent prompts, resulting in a reduction in input token costs and faster response times.</p><p>The Prompt Caching option is now available for Claude, OpenAI and Google Gemini models.</p></aside><h3>🏁 How it works</h3><ul><li>Go to <strong>Model Settings</strong></li><li>Expand the <strong>Advanced Model Parameter</strong></li><li>Scroll down to enable the “<strong>Prompt Caching</strong>” option</li></ul><p>Learn more <a href=\"https://docs.typingmind.com/prompts/automatic-prompt-caching\" target=\"_blank\" rel=\"noopener\">https://docs.typingmind.com/prompts/automatic-prompt-caching</a></p><figure><img src=\"/changelog/media/2024/gemini-context-caching/42e275f610.webp\" alt=\"Gemini Context Caching (screenshot 1 of 3)\" width=\"1598\" height=\"1276\" loading=\"lazy\" decoding=\"async\"></figure><figure><img src=\"/changelog/media/2024/gemini-context-caching/dc48e95dd5.webp\" alt=\"Gemini Context Caching (screenshot 2 of 3)\" width=\"2014\" height=\"1670\" loading=\"lazy\" decoding=\"async\"></figure><figure><img src=\"/changelog/media/2024/gemini-context-caching/6e8a4af475.webp\" alt=\"Gemini Context Caching (screenshot 3 of 3)\" width=\"1926\" height=\"1116\" loading=\"lazy\" decoding=\"async\"></figure><p><a href=\"https://x.com/TypingMindApp/status/1848660063898243266\" target=\"_blank\" rel=\"noopener\">See the announcement on X</a></p>"
}