{
  "slug": "ollama",
  "name": "Ollama",
  "url": "https://ollama.com",
  "cat": "ai",
  "group": "ai",
  "tagline": "Local model runner",
  "price": "Local runtime free and open source. Optional cloud: Free $0 (one model at a time), Pro $20/mo or $200/yr (3 models, 50x usage), Max $100/mo.",
  "tier": "mixed",
  "pick": false,
  "what": "An open-source runtime that downloads and serves open-weight models locally with one command, exposing both its own and an OpenAI-compatible API on localhost. A newer hosted cloud tier runs larger models on Ollama's servers through the same client.",
  "why": "Zero marginal cost and zero data egress — point your app at <code>localhost:11434</code> and iterate on prompts all day for free. Ideal for offline dev, privacy-sensitive features and CI tests that must not call a paid API.",
  "warn": "Local quality is capped by your RAM — a 7B quantised model is not Claude or GPT, and prompts tuned on it often break when moved to a frontier model. Cloud models do leave your machine.",
  "install": "curl -fsSL https://ollama.com/install.sh | sh",
  "category": {
    "key": "ai",
    "name": "Model APIs, routers & observability",
    "desc": "Providers, gateways, inference hosts and eval layers — constantly conflated, listed separately here.",
    "group": "ai",
    "groupName": "Put AI inside it"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": "https://ollama.com/",
    "checked_at": "2026-08-18T23:43:12.623+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}