> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter-d02e98a0-dev-127-conversation-state-store.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CreateGuardrailRequest

## Example Usage

```typescript theme={null}
import { CreateGuardrailRequest } from "@openrouter/sdk/models";

let value: CreateGuardrailRequest = {
  name: "My New Guardrail",
};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `allowedModels` | *string*\[] | :heavy\_minus\_sign: | Array of model identifiers (slug or canonical\_slug accepted) | \[<br />"openai/gpt-5.2",<br />"anthropic/claude-4.5-opus-20251124",<br />"deepseek/deepseek-r1-0528:free"<br />] |
| `allowedProviders` | *string*\[] | :heavy\_minus\_sign: | List of allowed provider IDs | \[<br />"openai",<br />"anthropic",<br />"deepseek"<br />] |
| `contentFilterBuiltins` | [models.ContentFilterBuiltinEntryInput](../models/contentfilterbuiltinentryinput.mdx)\[] | :heavy\_minus\_sign: | Builtin content filters to apply. The "flag" action is only supported for "regex-prompt-injection"; PII slugs (email, phone, ssn, credit-card, ip-address, person-name, address) accept "block" or "redact" only. | \[<br />\{<br />"action": "block",<br />"slug": "regex-prompt-injection"<br />}<br />] |
| `contentFilters` | [models.ContentFilterEntry](../models/contentfilterentry.mdx)\[] | :heavy\_minus\_sign: | Custom regex content filters to apply to request messages | \[<br />\{<br />"action": "redact",<br />"label": "\[API\_KEY]",<br />"pattern": "\b(sk-\[a-zA-Z0-9]\{48})\b"<br />}<br />] |
| `description` | *string* | :heavy\_minus\_sign: | Description of the guardrail | A guardrail for limiting API usage |
| ~~`enforceZdr`~~ | *boolean* | :heavy\_minus\_sign: | : warning: \*\* DEPRECATED \*\*: This will be removed in a future release, please migrate away from it as soon as possible.<br /><br />Deprecated. Use enforce\_zdr\_anthropic, enforce\_zdr\_openai, enforce\_zdr\_google, and enforce\_zdr\_other instead. When provided, its value is copied into any of those per-provider fields that are not explicitly specified on the request. | false |
| `enforceZdrAnthropic` | *boolean* | :heavy\_minus\_sign: | Whether to enforce zero data retention for Anthropic models. Falls back to enforce\_zdr when not provided. | false |
| `enforceZdrGoogle` | *boolean* | :heavy\_minus\_sign: | Whether to enforce zero data retention for Google models. Falls back to enforce\_zdr when not provided. | false |
| `enforceZdrOpenai` | *boolean* | :heavy\_minus\_sign: | Whether to enforce zero data retention for OpenAI models. Falls back to enforce\_zdr when not provided. | false |
| `enforceZdrOther` | *boolean* | :heavy\_minus\_sign: | Whether to enforce zero data retention for models that are not from Anthropic, OpenAI, or Google. Falls back to enforce\_zdr when not provided. | false |
| `ignoredModels` | *string*\[] | :heavy\_minus\_sign: | Array of model identifiers to exclude from routing (slug or canonical\_slug accepted) | \[<br />"openai/gpt-4o-mini"<br />] |
| `ignoredProviders` | *string*\[] | :heavy\_minus\_sign: | List of provider IDs to exclude from routing | \[<br />"azure"<br />] |
| `limitUsd` | *number* | :heavy\_minus\_sign: | Spending limit in USD | 50 |
| `name` | *string* | :heavy\_check\_mark: | Name for the new guardrail | My New Guardrail |
| `resetInterval` | [models.GuardrailInterval](../models/guardrailinterval.mdx) | :heavy\_minus\_sign: | Interval at which the limit resets (daily, weekly, monthly) | monthly |
| `workspaceId` | *string* | :heavy\_minus\_sign: | The workspace to create the guardrail in. Defaults to the default workspace if not provided. | 0df9e665-d932-5740-b2c7-b52af166bc11 |