{
  "slug": "jina-ai",
  "name": "Jina AI",
  "url": "https://jina.ai",
  "cat": "search",
  "group": "back",
  "tagline": "Reader, embeddings and reranker",
  "price": "Free API key on signup with a bundled token allowance, no card. Token-metered after that. Rate limits: Reader and Embeddings/Reranker 500 RPM, Search 100 RPM; premium raises Reader to 5K RPM and Search to 1K RPM.",
  "tier": "mixed",
  "pick": false,
  "what": "A set of small search-infrastructure APIs. Reader turns any URL into clean LLM-ready markdown by prefixing it with <code>r.jina.ai/</code>. Alongside it sit multilingual multimodal embeddings, a reranker for tightening retrieval precision, and a DeepSearch endpoint. All are plain HTTP, no SDK required.",
  "why": "The reranker is the cheapest single upgrade to a mediocre RAG pipeline — retrieve 50 chunks, rerank down to 5, and answer quality jumps. Reader needs no key at all for quick tests.",
  "warn": "Rate limits bite before token costs do. Keyless <code>r.jina.ai</code> requests get a much lower RPM ceiling and are throttled first under load.",
  "install": "curl https://r.jina.ai/https://example.com",
  "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://jina.ai/",
    "checked_at": "2026-08-18T17:12:38.21+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}