<!--
{
  "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/default",
  "metadataVersion" : "0.1.0",
  "role" : "Type Property",
  "symbol" : {
    "kind" : "Type Property",
    "modules" : [
      "Foundation Models",
      "FoundationModels"
    ],
    "preciseIdentifier" : "s:16FoundationModels19SystemLanguageModelC10GuardrailsV7defaultAEvpZ"
  },
  "title" : "default"
}
-->

# default

Guardrails that default to ensuring that the system blocks unsafe content in prompts and responses.

```
static let `default`: SystemLanguageModel.Guardrails
```

## Discussion

The `default` guardrail level means that all guardrails are turned on. When
the guardrails block unsafe content from either the prompt input or model response,
the framework throws a [`LanguageModelError.guardrailViolation(_:)`](/documentation/FoundationModels/LanguageModelError/guardrailViolation(_:)) error.

---

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)