{
  "opencollection": "1.0.0",
  "info": {
    "name": "Inferless Inference Model Management API",
    "version": "1.0"
  },
  "request": {
    "auth": {
      "type": "bearer",
      "token": "{{bearerToken}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Model Management",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Update a model's autoscaling and machine settings.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.inferless.com/rest/model/settings/update/",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Updates a deployed model's configuration including min/max replicas, scale-down delay, inference timeout, dedicated vs shared, machine type, and container concurrency."
        },
        {
          "info": {
            "name": "Retrieve runtime logs for a deployed model.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.inferless.com/rest/model/logs/get/",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Returns stdout/stderr log entries for a deployed model over a time range, with optional pagination via next_token."
        }
      ]
    }
  ],
  "bundled": true
}