{
  "slug": "pinecone",
  "name": "Pinecone",
  "url": "https://www.pinecone.io",
  "cat": "search",
  "group": "back",
  "tagline": "Hosted serverless vector DB",
  "price": "Starter free: 2GB storage, 2M write units/mo, 1M read units/mo, up to 5 indexes, 100 namespaces per index. Standard from $50/mo minimum usage (3-week trial includes $300 credits). Enterprise $500/mo minimum.",
  "tier": "mixed",
  "pick": false,
  "what": "The best-known managed vector database. Fully serverless — create an index, upsert vectors with metadata, query by similarity, and never size a node. Supports namespaces for multi-tenancy, metadata filtering, and integrated embedding and reranking models. Closed-source SaaS with no self-host option.",
  "why": "The lowest-friction path from embeddings to working RAG: no Docker, no schema, no index tuning. Nearly every LangChain and LlamaIndex tutorial uses it, so models write correct Pinecone code first try.",
  "warn": "Standard carries a <b>$50/mo minimum</b> whether you use it or not, and read/write units stay opaque until you have real traffic to measure.",
  "install": "npm i @pinecone-database/pinecone",
  "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://www.pinecone.io/",
    "checked_at": "2026-08-18T18:09:22.039+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}