<!--
{
  "availability" : [
    "iOS: 26.0.0 -",
    "iPadOS: 26.0.0 -",
    "macCatalyst: 26.0.0 -",
    "macOS: 26.0.0 -",
    "visionOS: 26.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "FoundationModels",
  "identifier" : "/documentation/FoundationModels/SystemLanguageModel/Guardrails/permissiveContentTransformations",
  "metadataVersion" : "0.1.0",
  "role" : "Type Property",
  "symbol" : {
    "kind" : "Type Property",
    "modules" : [
      "Foundation Models",
      "FoundationModels"
    ],
    "preciseIdentifier" : "s:16FoundationModels19SystemLanguageModelC10GuardrailsV32permissiveContentTransformationsAEvpZ"
  },
  "title" : "permissiveContentTransformations"
}
-->

# permissiveContentTransformations

Guardrails that allow for permissively transforming text input, including potentially unsafe
content, to text responses.

```
static let permissiveContentTransformations: SystemLanguageModel.Guardrails
```

## Discussion

The `permissiveContentTransform` guardrail model lets the model handle potentially
unsafe content, such as summarizing a news article. In this mode, requests you make to
the model that generate a `String` will not throw [`LanguageModelError.guardrailViolation(_:)`](/documentation/FoundationModels/LanguageModelError/guardrailViolation(_:))
errors. However, the model may still sometimes refuse to respond to a sensitive prompt, in which
case it generates a `String` refusal message.

When you generate responses other than `String`, this mode behaves the same way
as [`default`](/documentation/FoundationModels/SystemLanguageModel/Guardrails/default) mode and throws
[`LanguageModelError.guardrailViolation(_:)`](/documentation/FoundationModels/LanguageModelError/guardrailViolation(_:)) errors.

---

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)