List guardrail check types

> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usefini.com/llms.txt
> Use this file to discover all available pages before exploring further.

# List guardrail check types

> List guardrail check types through the workspace-scoped public API.

Returns an array describing available checks, their evaluation kind, repeatability, and configuration fields. The example shows one catalogue entry; the full response contains all six types.

See the [Guardrails overview](/en/api-reference/guardrails) for shared schemas and runtime limitations.

<ParamField header="Authorization" type="string" required>Bearer workspace API key. The key needs `read` scope.</ParamField>

## Response

<ResponseField name="[]" type="array">Descriptors with `type`, `label`, `description`, `evaluation` (`deterministic`, `llm`, or `hybrid`), `repeatable`, and `configFields`. Each field has `key`, `label`, `description`, `kind`, and `required`.</ResponseField>

<RequestExample>
  ~~~bash cURL theme={null}
  curl --request GET \
    --url "https://api-prod.usefini.com/v2/guardrail-policies/check-types/public" \
    --header "Authorization: Bearer $FINI_API_KEY"
  ~~~

  ~~~javascript Node.js theme={null}
  const response = await fetch("https://api-prod.usefini.com/v2/guardrail-policies/check-types/public", {
    method: "GET",
    headers: { Authorization: `Bearer ${process.env.FINI_API_KEY}` },
  });
  if (!response.ok) throw new Error(`HTTP ${response.status}`);
  console.log(await response.json());
  ~~~

  ~~~python Python theme={null}
  import os
  import requests

  response = requests.get(
      "https://api-prod.usefini.com/v2/guardrail-policies/check-types/public",
      headers={"Authorization": f"Bearer {os.environ['FINI_API_KEY']}"},
      timeout=30,
  )
  response.raise_for_status()
  print(response.json())
  ~~~
</RequestExample>

<ResponseExample>
  ~~~json 200 theme={null}
  [
    {
      "type": "banned_terms",
      "label": "Banned terms",
      "description": "Blocks replies that mention listed words, phrases (competitors, forbidden products) or match regular expressions. Case-insensitive, whole-word matching.",
      "evaluation": "deterministic",
      "repeatable": false,
      "configFields": [
        {
          "key": "terms",
          "label": "Terms",
          "description": "Words or phrases matched as whole words, case-insensitive.",
          "kind": "string_list",
          "required": false
        },
        {
          "key": "patterns",
          "label": "Regex patterns",
          "description": "JavaScript regular expressions (case-insensitive, unicode). Keep them simple; nested repetitions are rejected.",
          "kind": "regex_list",
          "required": false
        }
      ]
    }
  ]
  ~~~
</ResponseExample>


## Related topics

- [Overview](/en/api-reference/guardrails.md)
- [Guardrails](/en/configuration/guardrails.md)
- [List guardrail policies](/en/api-reference/list-guardrail-policies.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.