Create policy | Lakera API documentation

1 curl -X POST https://platform.lakera.ai/api/v1-beta/policies \ 2 -H "Authorization: Bearer <token>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "name": "string", 6 "policy_mode": "IO", 7 "input_detectors": [ 8 { 9 "type": "prompt_attack", 10 "threshold": "l1_confident" 11 } 12 ], 13 "output_detectors": [ 14 { 15 "type": "prompt_attack", 16 "threshold": "l1_confident" 17 } 18 ] 19 }'

1 { 2 "status": "ok", 3 "message": "string", 4 "id": "string", 5 "data": { 6 "name": "string", 7 "policy_mode": "IO", 8 "input_detectors": [ 9 { 10 "type": "prompt_attack", 11 "threshold": "l1_confident", 12 "override_list": [ 13 "string" 14 ], 15 "allowed_domains": [ 16 "my-trusted-domain.com", 17 "another-safe-domain.com" 18 ] 19 } 20 ], 21 "output_detectors": [ 22 { 23 "type": "prompt_attack", 24 "threshold": "l1_confident", 25 "override_list": [ 26 "string" 27 ], 28 "allowed_domains": [ 29 "my-trusted-domain.com", 30 "another-safe-domain.com" 31 ] 32 } 33 ] 34 } 35 }

Create a new policy configuration

Authentication

AuthorizationBearer

Bearer authentication using API key. Generate an API key from the Lakera platform. Example: Bearer sk_123…

Request

This endpoint expects an object.

namestringRequired

A descriptive name for the policy

policy_modeenumRequired

Set to "IO" for screening model inputs and outputs

Allowed values:

input_detectorslist of objectsRequired

List of detector configurations to apply to LLM inputs

output_detectorslist of objectsRequired

List of detector configurations to apply to LLM outputs

Response

Policy created successfully

statusenum or null

Response status

Allowed values:

messagestring or null

Human-readable response message

idstring or null

Policy ID

dataobject or null

Policy details