[
  {
    "id": "ollama-gpu",
    "type": "ollama",
    "url": "http://host.docker.internal:11434",
    "models": [
      { "id": "qwen3.5:9b-q8_0", "capabilities": ["chat"], "priority": 1 },
      { "id": "qwen3-vl:8b", "capabilities": ["chat", "vision"], "priority": 1 }
    ],
    "access": "all",
    "rate_limit": null
  }
]