Orq.ai Guardrail Rules API

Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace.

Operations 6

GET /v2/guardrail-rules List guardrail rules #
POST /v2/guardrail-rules Create a guardrail rule #
GET /v2/guardrail-rules/used-guardrails List guardrails used by guardrail rules #
GET /v2/guardrail-rules/{guardrail_rule_id} Retrieve a guardrail rule #
DELETE /v2/guardrail-rules/{guardrail_rule_id} Delete a guardrail rule #
PATCH /v2/guardrail-rules/{guardrail_rule_id} Update a guardrail rule #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/orq:orq-guardrail-rules-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

orq-guardrail-rules-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: orq.ai Guardrail Rules API
  version: '2.0'
  description: orq.ai API documentation
servers:
- url: https://my.orq.ai
security:
- ApiKey: []
tags:
- name: Guardrail Rules
  description: Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace.
paths:
  /v2/guardrail-rules:
    get:
      tags:
      - Guardrail Rules
      summary: List guardrail rules
      description: Returns guardrail rules with cursor pagination, search, status, project, sort, and referenced-guardrail filters.
      operationId: GuardrailRuleList
      parameters:
      - name: limit
        in: query
        schema:
          type: integer
          format: int32
      - name: starting_after
        in: query
        schema:
          type: string
      - name: ending_before
        in: query
        schema:
          type: string
      - name: project_id
        in: query
        schema:
          type: string
      - name: search
        in: query
        schema:
          type: string
      - name: sort_by
        in: query
        schema:
          type: string
      - name: enabled
        in: query
        schema:
          type: boolean
      - name: guardrail_id
        in: query
        schema:
          type: array
          items:
            type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListGuardrailRulesResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: list
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: list
      x-code-samples:
      - lang: curl
        label: Core - List guardrail rules
        source: "curl --get 'https://my.orq.ai/v2/guardrail-rules' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\" \\\n  --data-urlencode 'limit=25'\n"
    post:
      tags:
      - Guardrail Rules
      summary: Create a guardrail rule
      description: Creates a guardrail rule with metadata and optional evaluator, plugin, and matching configuration. Rules default to disabled when `enabled` is omitted.
      operationId: GuardrailRuleCreate
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateGuardrailRuleRequest'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateGuardrailRuleResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: create
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: create
      x-code-samples:
      - lang: curl
        label: Core - Create guardrail rule
        source: "curl --request POST \\\n  --url 'https://my.orq.ai/v2/guardrail-rules' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\" \\\n  --header 'Content-Type: application/json' \\\n  --data '{\n    \"display_name\": \"Protect customer data\",\n    \"description\": \"Blocks sensitive customer data from model output.\",\n    \"enabled\": true,\n    \"guardrails\": [{\n      \"id\": \"orq_pii_detection\",\n      \"execute_on\": \"output\",\n      \"sample_rate\": 1,\n      \"is_guardrail\": true\n    }]\n  }'\n"
      - lang: python
        label: Python - Create guardrail rule
        source: "import os\nfrom orq_ai_sdk import Orq\n\nclient = Orq(api_key=os.environ[\"ORQ_API_KEY\"])\nrule = client.guardrail_rules.create(\n    display_name=\"Protect customer data\",\n    description=\"Blocks sensitive customer data from model output.\",\n    enabled=True,\n    guardrails=[{\n        \"id\": \"orq_pii_detection\",\n        \"execute_on\": \"output\",\n        \"sample_rate\": 1,\n        \"is_guardrail\": True,\n    }],\n)\n\nprint(rule._id)\n"
      - lang: typescript
        label: Node.js - Create guardrail rule
        source: "import { Orq } from '@orq-ai/node';\n\nconst client = new Orq({ apiKey: process.env.ORQ_API_KEY });\nconst rule = await client.guardrailRules.create({\n  displayName: 'Protect customer data',\n  description: 'Blocks sensitive customer data from model output.',\n  enabled: true,\n  guardrails: [{\n    id: 'orq_pii_detection',\n    executeOn: 'output',\n    sampleRate: 1,\n    isGuardrail: true,\n  }],\n});\n\nconsole.log(rule._id);\n"
  /v2/guardrail-rules/used-guardrails:
    get:
      tags:
      - Guardrail Rules
      summary: List guardrails used by guardrail rules
      description: Returns the distinct guardrail identifiers used by guardrail rules in the requested scope.
      operationId: GuardrailRuleListUsedGuardrails
      parameters:
      - name: project_id
        in: query
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListGuardrailRuleUsedGuardrailsResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: listUsedGuardrails
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: listUsedGuardrails
      x-code-samples:
      - lang: curl
        label: Core - List guardrails used by rules
        source: "curl --request GET \\\n  --url 'https://my.orq.ai/v2/guardrail-rules/used-guardrails' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\"\n"
  /v2/guardrail-rules/{guardrail_rule_id}:
    get:
      tags:
      - Guardrail Rules
      summary: Retrieve a guardrail rule
      description: Retrieves a guardrail rule by its unique identifier.
      operationId: GuardrailRuleGet
      parameters:
      - name: guardrail_rule_id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetGuardrailRuleResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Not permitted for this key, project or workspace. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: retrieve
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: retrieve
      x-code-samples:
      - lang: curl
        label: Core - Retrieve guardrail rule
        source: "curl --request GET \\\n  --url 'https://my.orq.ai/v2/guardrail-rules/grl_01HZXW2K7Y8Q9M0N1P2R3S4T5V' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\"\n"
    delete:
      tags:
      - Guardrail Rules
      summary: Delete a guardrail rule
      description: Permanently deletes a guardrail rule.
      operationId: GuardrailRuleDelete
      parameters:
      - name: guardrail_rule_id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteGuardrailRuleResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: delete
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: delete
      x-code-samples:
      - lang: curl
        label: Core - Delete guardrail rule
        source: "curl --request DELETE \\\n  --url 'https://my.orq.ai/v2/guardrail-rules/grl_01HZXW2K7Y8Q9M0N1P2R3S4T5V' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\"\n"
    patch:
      tags:
      - Guardrail Rules
      summary: Update a guardrail rule
      description: Partially updates guardrail-rule metadata or configuration. Project scope is immutable.
      operationId: GuardrailRuleUpdate
      parameters:
      - name: guardrail_rule_id
        in: path
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpdateGuardrailRuleRequest'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UpdateGuardrailRuleResponse'
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-speakeasy-group: guardrailRules
      x-speakeasy-name-override: update
      x-cli-hidden: true
      x-cli-group: guardrailRules
      x-cli-name: update
      x-code-samples:
      - lang: curl
        label: Core - Configure guardrail rule
        source: "curl --request PATCH \\\n  --url 'https://my.orq.ai/v2/guardrail-rules/grl_01HZXW2K7Y8Q9M0N1P2R3S4T5V' \\\n  --header \"Authorization: Bearer $ORQ_API_KEY\" \\\n  --header 'Content-Type: application/json' \\\n  --data '{\n    \"enabled\": true,\n    \"expression\": {\"cel\": \"model == '\\''openai/gpt-5'\\''\"},\n    \"guardrails\": [{\n      \"id\": \"orq_pii_detection\",\n      \"execute_on\": \"output\",\n      \"sample_rate\": 1,\n      \"is_guardrail\": true\n    }]\n  }'\n"
components:
  schemas:
    UpdateGuardrailRuleRequest:
      required: []
      type: object
      properties:
        display_name:
          type: string
        description:
          type: string
        enabled:
          type: boolean
        expression:
          $ref: '#/components/schemas/GuardrailRuleExpression'
        guardrails:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRuleGuardrail'
        plugins:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRulePlugin'
    GuardrailRuleGuardrail:
      required:
      - id
      - execute_on
      type: object
      properties:
        id:
          type: string
        execute_on:
          type: string
        sample_rate:
          type: number
          format: double
        is_guardrail:
          type: boolean
        options:
          type: object
    GuardrailRuleExpression:
      type: object
      properties:
        config:
          type: object
        cel:
          type: string
          description: CEL expression used to match requests. Empty means the rule always matches.
    GuardrailRulePlugin:
      type: object
      properties:
        id:
          type: string
          description: Plugin discriminator.
        language:
          type: string
          description: "Languages, regions and entity types are checked against the live\n pii-detection capabilities catalog when the rule is saved, not pinned\n here, so a language or region the detector gains becomes writable without\n a future update."
        entities:
          type: array
          items:
            type: string
          description: Entity types to redact. On their own a strict allowlist; alongside regions they add to the region coverage.
        on_failure:
          type: string
        threshold:
          type: number
          format: double
        regions:
          type: array
          items:
            type: string
          description: 'Regions of coverage by ISO 3166-1 alpha-2 code, or ["all"]. Combines with entities: the two selections are unioned.'
        entity_thresholds:
          type: object
          additionalProperties:
            type: number
            format: double
          description: Per-entity-type confidence cutoff. Every key must also appear in entities.
    GetGuardrailRuleResponse:
      required:
      - guardrail_rule
      type: object
      properties:
        guardrail_rule:
          $ref: '#/components/schemas/GuardrailRule'
    DeleteGuardrailRuleResponse:
      type: object
      properties: {}
    ListGuardrailRuleUsedGuardrailsResponse:
      required:
      - object
      - guardrail_ids
      type: object
      properties:
        object:
          type: string
        guardrail_ids:
          type: array
          items:
            type: string
    CreateGuardrailRuleRequest:
      required:
      - display_name
      type: object
      properties:
        display_name:
          type: string
        description:
          type: string
        project_id:
          type: string
          description: Optional project scope. Omit for a workspace-wide rule.
        enabled:
          type: boolean
          description: Whether the rule is active. Defaults to false when omitted.
        expression:
          $ref: '#/components/schemas/GuardrailRuleExpression'
        guardrails:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRuleGuardrail'
        plugins:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRulePlugin'
    ListGuardrailRulesResponse:
      required:
      - object
      - data
      - has_more
      type: object
      properties:
        object:
          type: string
        data:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRule'
        has_more:
          type: boolean
    ErrorResponse:
      type: object
      properties:
        message:
          type: string
          description: Human-readable error message.
        code:
          type: integer
          description: gRPC status code, when the service reports one.
        details:
          type: array
          items: {}
          description: Additional error details, when the service reports any.
      required:
      - message
    UpdateGuardrailRuleResponse:
      required:
      - guardrail_rule
      type: object
      properties:
        guardrail_rule:
          $ref: '#/components/schemas/GuardrailRule'
    GuardrailRule:
      required:
      - id
      - created_at
      - updated_at
      - created_by_id
      - updated_by_id
      - project_id
      - display_name
      - description
      - enabled
      - guardrails
      - plugins
      type: object
      properties:
        id:
          type: string
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
        created_by_id:
          type: string
        updated_by_id:
          type: string
        project_id:
          type: string
          description: Project that contains the rule. Empty for workspace-wide rules.
        display_name:
          type: string
          description: Human-readable guardrail-rule name.
        description:
          type: string
        enabled:
          type: boolean
        expression:
          $ref: '#/components/schemas/GuardrailRuleExpression'
        guardrails:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRuleGuardrail'
        plugins:
          type: array
          items:
            $ref: '#/components/schemas/GuardrailRulePlugin'
    CreateGuardrailRuleResponse:
      required:
      - guardrail_rule
      type: object
      properties:
        guardrail_rule:
          $ref: '#/components/schemas/GuardrailRule'
  securitySchemes:
    ApiKey:
      type: http
      scheme: bearer
      bearerFormat: JWT
externalDocs:
  url: https://docs.orq.ai
  description: orq.ai Documentation
x-speakeasy-timeout: 600000