<!--
{
  "availability" : [
    "iOS: 13.0.0 -",
    "iPadOS: 13.0.0 -",
    "macCatalyst: 13.1.0 -",
    "macOS: 10.15.0 -",
    "tvOS: 13.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Vision",
  "identifier" : "/documentation/Vision/VNCoreMLModel/featureProvider",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Property",
  "symbol" : {
    "kind" : "Instance Property",
    "modules" : [
      "Vision"
    ],
    "preciseIdentifier" : "c:objc(cs)VNCoreMLModel(py)featureProvider"
  },
  "title" : "featureProvider"
}
-->

# featureProvider

An optional object to support inputs outside Vision.

```
var featureProvider: (any MLFeatureProvider)? { get set }
```

## Discussion

This optional object conforms to the <doc://com.apple.documentation/documentation/CoreML/MLFeatureProvider> protocol that the model uses to predict inputs that are not supplied by Vision. Vision provides the MLModel with the image for the [`inputImageFeatureName`](/documentation/Vision/VNCoreMLModel/inputImageFeatureName) via the `VNRequestHandler`.

A feature provider is necessary for models that have more than one required input. Models with only one image input won’t use the feature provider.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)