{
  "client": {
    "drop_excess_requests": false
  },
  "providers": {
    "ollama": {
      "keys": [
        {
          "name": "ollama-gpu",
          "value": "dummy",
          "models": [
            "qwen2.5:0.5b",
            "qwen2.5:1.5b",
            "qwen3:4b",
            "gemma3:4b",
            "qwen3:8b"
          ],
          "weight": 1.0
        }
      ],
      "network_config": {
        "base_url": "http://host.docker.internal:11436",
        "default_request_timeout_in_seconds": 300,
        "max_retries": 2,
        "retry_backoff_initial_ms": 500,
        "retry_backoff_max_ms": 10000
      }
    },
    "ollama-cpu": {
      "keys": [
        {
          "name": "ollama-cpu-key",
          "value": "dummy",
          "models": [
            "gemma3:1b",
            "qwen2.5:1.5b",
            "qwen2.5:3b"
          ],
          "weight": 1.0
        }
      ],
      "network_config": {
        "base_url": "http://host.docker.internal:11435",
        "default_request_timeout_in_seconds": 120,
        "max_retries": 2,
        "retry_backoff_initial_ms": 500,
        "retry_backoff_max_ms": 10000
      },
      "custom_provider_config": {
        "base_provider_type": "openai",
        "allowed_requests": {
          "chat_completion": true,
          "chat_completion_stream": true
        }
      }
    }
  }
}