{
  "slug": "modal",
  "name": "Modal",
  "url": "https://modal.com",
  "cat": "ai",
  "group": "ai",
  "tagline": "Serverless GPU compute platform",
  "price": "Per second. H100 $0.001097/s (~$3.95/hr), B200 $0.001736/s, A100 40GB $0.000583/s, T4 $0.000164/s; CPU $0.0000131/core-s. Starter $0 with $30/mo free credits; Team $250/mo with $100 credits.",
  "tier": "mixed",
  "pick": false,
  "what": "Serverless compute for Python: decorate a function and Modal containerises it and runs it on GPUs with fast cold starts and scale-to-zero. It is <b>infrastructure</b>, not a model API — you bring the model, the weights and the code.",
  "why": "For when no hosted endpoint exists: custom fine-tunes, unusual pipelines, batch jobs, or an embedding service you want to own. The $30 of free credits each month covers a real side project.",
  "warn": "You own the ops — model loading, memory sizing and concurrency are your problem, and a container that fails to scale to zero bills GPU seconds continuously. Starter caps you at 10 concurrent GPUs.",
  "install": "pip install modal && modal setup",
  "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://modal.com/",
    "checked_at": "2026-08-18T23:43:12.623+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}