{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigrmwxob3na2sbo7t6v7dqoi4mj7eklzj6mfeclnsvdmaxlrwhq2e",
    "uri": "at://did:plc:haakkg7y3xdghcdmprxeexso/app.bsky.feed.post/3mj4tdumc2a72"
  },
  "path": "/t/any-good-openrouter-interface-which-is-private-and-secure/36916#post_12",
  "publishedAt": "2026-04-10T05:52:24.000Z",
  "site": "https://discuss.privacyguides.net",
  "tags": [
    "docs.openwebui.com",
    "❓ FAQ / Open WebUI",
    "Performance Tips Guide",
    "Memory & Personalization / Open WebUI"
  ],
  "textContent": "Dellsam1:\n\n> the only problem now is I can’t seem to find a way to limit my messages sent to api\n\nHere you go:\n\ndocs.openwebui.com\n\n### ❓ FAQ / Open WebUI\n\nQ: How can I get support or ask for help?\n\n> ### Q: Why am I seeing multiple API requests when I only send one message? Why is my token usage higher than expected?\n>\n> **A:** Open WebUI uses **Task Models** to power background features that enhance your chat experience. When you send a single message, additional API calls may be made for:\n>\n>   * **Title Generation** : Automatically generating a title for new chats\n>   * **Tag Generation** : Auto-tagging chats for organization\n>   * **Query Generation** : Creating optimized search queries for RAG (when you attach files or knowledge)\n>   * **Web Search Queries** : Generating search terms when web search is enabled\n>   * **Autocomplete Suggestions** : If enabled\n>\n\n>\n> By default, these tasks use the **same model** you’re chatting with. If you’re using an expensive API model (like GPT-4 or Claude), this can significantly increase your costs.\n>\n> **To reduce API costs:**\n>\n>   1. Go to **Admin Panel > Settings > Interface** (for title/tag generation settings)\n>   2. Configure a **Task Model** under **Admin Panel > Settings > Models** to use a smaller, cheaper model (like GPT-4o-mini) or a local model for background tasks\n>   3. Disable features you don’t need (auto-title, auto-tags, etc.)\n>\n\n>\n>> Cost-Saving Recommendation\n>>\n>> Set your Task Model to a fast, inexpensive model (or a local model via Ollama) while keeping your primary chat model as a more capable one. This gives you the best of both worlds: smart responses for your conversations, cheap/free processing for background tasks.\n>\n> For more optimization tips, see the **Performance Tips Guide**.\n\nDellsam1:\n\n> I was also hoping for a chatgpt style memory\n\nMemory is currently beta/experimental:\n\ndocs.openwebui.com\n\n### Memory & Personalization / Open WebUI\n\nThe Memory system is currently in Beta/Experimental stage. You may encounter inconsistencies in how models store or retrieve information, and storage formats may change in future updates.",
  "title": "Any good openrouter interface which is private and secure?"
}