CreateGuardrailRequest - TypeScript SDK

CreateGuardrailRequest type definition

Example Usage

1 import { CreateGuardrailRequest } from "@openrouter/sdk/models";
2 
3 let value: CreateGuardrailRequest = {
4   name: "My New Guardrail",
5 };

Fields

Field	Type	Required	Description	Example
`allowedModels`	string[]	➖	Array of model identifiers (slug or canonical_slug accepted)	[ “openai/gpt-5.2”, “anthropic/claude-4.5-opus-20251124”, “deepseek/deepseek-r1-0528:free” ]
`allowedProviders`	string[]	➖	List of allowed provider IDs	[ “openai”, “anthropic”, “deepseek” ]
`contentFilterBuiltins`	models.ContentFilterBuiltinEntry[]	➖	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.	[ `{"action": "block","slug": "regex-prompt-injection"}` ]
`contentFilters`	models.ContentFilterEntry[]	➖	Custom regex content filters to apply to request messages	[ `{"action": "redact","label": "[API_KEY]","pattern": "\\b(sk-[a-zA-Z0-9]{48}`)\b” } ]
`description`	string	➖	Description of the guardrail	A guardrail for limiting API usage
~~`enforceZdr`~~	boolean	➖	: warning: DEPRECATED : This will be removed in a future release, please migrate away from it as soon as possible. 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	➖	Whether to enforce zero data retention for Anthropic models. Falls back to enforce_zdr when not provided.	false
`enforceZdrGoogle`	boolean	➖	Whether to enforce zero data retention for Google models. Falls back to enforce_zdr when not provided.	false
`enforceZdrOpenai`	boolean	➖	Whether to enforce zero data retention for OpenAI models. Falls back to enforce_zdr when not provided.	false
`enforceZdrOther`	boolean	➖	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[]	➖	Array of model identifiers to exclude from routing (slug or canonical_slug accepted)	[ “openai/gpt-4o-mini” ]
`ignoredProviders`	string[]	➖	List of provider IDs to exclude from routing	[ “azure” ]
`limitUsd`	number	➖	Spending limit in USD	50
`name`	string	✔️	Name for the new guardrail	My New Guardrail
`resetInterval`	models.GuardrailInterval	➖	Interval at which the limit resets (daily, weekly, monthly)	monthly
`workspaceId`	string	➖	The workspace to create the guardrail in. Defaults to the default workspace if not provided.	0df9e665-d932-5740-b2c7-b52af166bc11

Example Usage

1 import { CreateGuardrailRequest } from "@openrouter/sdk/models";
2 
3 let value: CreateGuardrailRequest = {
4   name: "My New Guardrail",
5 };

Fields

Field	Type	Required	Description	Example
`allowedModels`	string[]	➖	Array of model identifiers (slug or canonical_slug accepted)	[ “openai/gpt-5.2”, “anthropic/claude-4.5-opus-20251124”, “deepseek/deepseek-r1-0528:free” ]
`allowedProviders`	string[]	➖	List of allowed provider IDs	[ “openai”, “anthropic”, “deepseek” ]
`contentFilterBuiltins`	models.ContentFilterBuiltinEntry[]	➖	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.	[ `{"action": "block","slug": "regex-prompt-injection"}` ]
`contentFilters`	models.ContentFilterEntry[]	➖	Custom regex content filters to apply to request messages	[ `{"action": "redact","label": "[API_KEY]","pattern": "\\b(sk-[a-zA-Z0-9]{48}`)\b” } ]
`description`	string	➖	Description of the guardrail	A guardrail for limiting API usage
~~`enforceZdr`~~	boolean	➖	: warning: DEPRECATED : This will be removed in a future release, please migrate away from it as soon as possible. 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	➖	Whether to enforce zero data retention for Anthropic models. Falls back to enforce_zdr when not provided.	false
`enforceZdrGoogle`	boolean	➖	Whether to enforce zero data retention for Google models. Falls back to enforce_zdr when not provided.	false
`enforceZdrOpenai`	boolean	➖	Whether to enforce zero data retention for OpenAI models. Falls back to enforce_zdr when not provided.	false
`enforceZdrOther`	boolean	➖	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[]	➖	Array of model identifiers to exclude from routing (slug or canonical_slug accepted)	[ “openai/gpt-4o-mini” ]
`ignoredProviders`	string[]	➖	List of provider IDs to exclude from routing	[ “azure” ]
`limitUsd`	number	➖	Spending limit in USD	50
`name`	string	✔️	Name for the new guardrail	My New Guardrail
`resetInterval`	models.GuardrailInterval	➖	Interval at which the limit resets (daily, weekly, monthly)	monthly
`workspaceId`	string	➖	The workspace to create the guardrail in. Defaults to the default workspace if not provided.	0df9e665-d932-5740-b2c7-b52af166bc11

1	import { CreateGuardrailRequest } from "@openrouter/sdk/models";
2
3	let value: CreateGuardrailRequest = {
4	name: "My New Guardrail",
5	};