{
  "slug": "qdrant",
  "name": "Qdrant",
  "url": "https://qdrant.tech",
  "cat": "search",
  "group": "back",
  "tagline": "Open-source vector DB + cloud",
  "price": "OSS free (Apache 2.0). Cloud free tier forever: 1GB RAM, 0.5 vCPU, 4GB disk, single node. Standard is usage-based hourly for compute, memory, storage and backup. Premium has a minimum spend. Hybrid and Private Cloud are custom.",
  "tier": "mixed",
  "pick": false,
  "what": "A Rust vector database with the strongest payload filtering in the category — combine vector similarity with keyword, full-text, numeric-range, geo and boolean conditions in one query. Supports hybrid search with reciprocal rank fusion, sharding, multitenancy, GPU indexing, and quantization that cuts RAM by up to 97%.",
  "why": "The best free-forever managed tier of any serious vector DB: 1GB RAM with no clock running is enough for a real side project, and <code>docker run qdrant/qdrant</code> is identical locally.",
  "warn": "The free cluster is a single node with no backups and no HA — a prototype home, not a production one. Filtered search over high-cardinality payloads needs index planning.",
  "install": "docker run -p 6333:6333 qdrant/qdrant",
  "category": {
    "key": "search",
    "name": "Search, vector & RAG",
    "desc": "Keyword search, vector stores, and web-search APIs for agents — three different things.",
    "group": "back",
    "groupName": "Give it a backend"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": "https://qdrant.tech/",
    "checked_at": "2026-08-18T18:09:22.039+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}