Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "fal",
  "url": "https://fal.ai/docs/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://fal.ai/docs/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://fal.ai/docs/",
    "organization": "fal"
  },
  "documentationUrl": "https://fal.ai/docs/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "fal",
      "name": "fal",
      "description": "Use when building AI applications that call 1,000+ production models (image, video, audio generation) via API, or when deploying custom models to serverless GPU infrastructure with autoscaling. Reach for fal when you need to integrate generative media into applications, test models before committing, or run inference at scale without managing infrastructure.",
      "tags": [],
      "url": "https://fal.ai/docs/.well-known/agent-skills/fal/skill.md"
    }
  ]
}