<!--
{
  "availability" : [
    "iOS: 11.0.0 -",
    "iPadOS: 11.0.0 -",
    "macCatalyst: 13.1.0 -",
    "macOS: 10.13.0 -",
    "tvOS: 11.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Vision",
  "identifier" : "/documentation/Vision/VNCoreMLModel",
  "metadataVersion" : "0.1.0",
  "role" : "Class",
  "symbol" : {
    "kind" : "Class",
    "modules" : [
      "Vision"
    ],
    "preciseIdentifier" : "c:objc(cs)VNCoreMLModel"
  },
  "title" : "VNCoreMLModel"
}
-->

# VNCoreMLModel

A container for the model to use with Vision requests.

```
class VNCoreMLModel
```

## Overview

A <doc://com.apple.documentation/documentation/CoreML> model encapsulates the information trained from a data set used to drive Vision recognition requests. See <doc://com.apple.documentation/documentation/CoreML/getting-a-core-ml-model> for instructions on training your own model. Once you train the model, use this class to initialize a [`VNCoreMLRequest`](/documentation/Vision/VNCoreMLRequest) for identification.

## Topics

### Initializing a Model

[`init(for:)`](/documentation/Vision/VNCoreMLModel/init(for:))

Creates a model container to use with a Core ML request.

[`init(forMLModel:)`](/documentation/Vision/VNCoreMLModel/init(forMLModel:))

### Providing Features

[`featureProvider`](/documentation/Vision/VNCoreMLModel/featureProvider)

An optional object to support inputs outside Vision.

[`inputImageFeatureName`](/documentation/Vision/VNCoreMLModel/inputImageFeatureName)

The name of the feature value that Vision sets from the request handler.


---

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)