Skip to main content

​
Policies API

Policies allow you to control how Perf routes requests and handles content. Set model preferences, enforce cost limits, detect PII, and filter sensitive terms.

​
Why Policies?

  • Cost Control: Set budget limits and prefer cheaper models
  • Compliance: Block specific providers or require certain models
  • Security: Detect and redact PII from outputs
  • Governance: Monitor and control content with term filtering

​
Policy Types

TypeDescriptionAvailable Tiers
routingModel selection and routing rulesAll tiers
contentPII detection and term filteringPro, Growth, Team, Enterprise

​
Policy Templates API

Get pre-built policy templates to quickly enable common configurations.

​
List Templates

GET https://api.withperf.pro/v1/policies/templates
Response: 
{
  "templates": [
    {
      "slug": "budget-mode",
      "name": "Budget Mode",
      "description": "Aggressive cost optimization - prefer cheapest models",
      "category": "cost",
      "policy_type": "routing",
      "config": {
        "prefer_cheaper_models": true,
        "cost_ceiling_usd": 0.01
      }
    },
    {
      "slug": "pii-protection",
      "name": "PII Protection",
      "description": "Detect and redact PII from outputs",
      "category": "compliance",
      "policy_type": "content",
      "config": {
        "pii_detection": {
          "enabled": true,
          "types": ["ssn", "credit_card", "email"],
          "action": "redact"
        }
      }
    }
  ]
}

​
Get Template by Slug

GET https://api.withperf.pro/v1/policies/templates/{slug}
Example: 
curl https://api.withperf.pro/v1/policies/templates/budget-mode \
  -H "Authorization: Bearer pk_live_abc123"

​
Available Templates

​
Routing Templates

TemplateSlugCategoryDescription
Budget Modebudget-modecostPrefer cheapest models, set cost ceiling
Performance Modeperformance-modeperformanceOptimize for low latency
Quality Modequality-modeperformanceMaximize output quality with best models
No OpenAIno-openaicomplianceBlock all OpenAI models
No Anthropicno-anthropiccomplianceBlock all Anthropic models
Google Onlygoogle-onlycomplianceOnly use Google Gemini models

​
Content Templates (Pro+)

TemplateSlugCategoryDescription
PII Protectionpii-protectioncomplianceDetect and redact PII from outputs
Healthcare Compliancehealthcare-compliancecomplianceMedical context awareness + PII detection
Child-Safe Contentchild-safecomplianceAge-appropriate content enforcement
Professional Communicationprofessional-communicationcomplianceBusiness-appropriate tone
Custom Terms Filtercustom-terms-filtercomplianceBlock or require specific terms

​
Routing Policy Options

Configure how Perf selects models:
OptionTypeDescription
model_allow_liststring[]Only allow these specific models
model_block_liststring[]Block these models from selection
provider_allow_liststring[]Only use these providers (openai, anthropic, google)
provider_block_liststring[]Block these providers
cost_ceiling_usdnumberMaximum cost per API call
prefer_cheaper_modelsbooleanPrefer lower-cost models when quality is similar
latency_target_msnumberTarget maximum latency
prefer_faster_modelsbooleanPrefer lower-latency models
on_violationstringAction: info, warn, soft_block, hard_block
Example - Google Only Policy: 
{
  "name": "Google Only",
  "policy_type": "routing",
  "config": {
    "provider_allow_list": ["google"],
    "on_violation": "hard_block"
  }
}

​
Content Policy Options

Configure content filtering and PII detection:
OptionTypeDescription
evaluate_outputbooleanEvaluate model output (default: true)
pii_detection.enabledbooleanEnable PII detection
pii_detection.typesstring[]PII types to detect
pii_detection.actionstringAction: warn, redact, block
pii_detection.redaction_formatstringRedaction text (default: [REDACTED])
blocked_terms.enabledbooleanEnable blocked term detection
blocked_terms.termsstring[]List of terms to block
blocked_terms.actionstringAction: warn, redact, block
on_violationstringOverall violation action
Example - PII Protection Policy: 
{
  "name": "PII Protection",
  "policy_type": "content",
  "config": {
    "evaluate_output": true,
    "pii_detection": {
      "enabled": true,
      "types": ["ssn", "credit_card", "email", "phone_us"],
      "action": "redact",
      "redaction_format": "[REDACTED]"
    },
    "on_violation": "soft_block"
  }
}

​
Supported PII Types

TypePatternDescription
ssnXXX-XX-XXXXSocial Security Numbers
ssn_no_dashXXXXXXXXXSSN without dashes
credit_card13-19 digitsCredit cards (with Luhn validation)
emailuser@domain.comEmail addresses
phone_us(XXX) XXX-XXXXUS phone numbers
ip_addressX.X.X.XIPv4 addresses
date_of_birthMM/DD/YYYYDates of birth

​
Violation Actions

ActionDescription
infoLog only (audit mode) - request proceeds
warnLog warning - request proceeds with warning in response
soft_blockApply modifications (redact PII, override model) - request proceeds
hard_blockReject request with 403 error

​
Policy Blocked Response

When a request is blocked by a hard_block policy: 
{
  "error": "Request blocked by policy",
  "code": "POLICY_BLOCKED",
  "message": "Request blocked by policy: Model gpt-4o-mini is not in allow list",
  "policy_evaluation": {
    "result": "hard_block",
    "violations": [
      {
        "policy_name": "Google Only",
        "rule": "model_allow_list",
        "message": "Model gpt-4o-mini is not in allow list"
      }
    ]
  }
}

​
Managing Policies via Dashboard

Policies are configured per-project in the Perf Dashboard:
  1. Navigate to Configure > Policies
  2. Click Create Policy or Apply Template
  3. Configure rules and violation actions
  4. Set priority (lower number = higher priority)
  5. Enable the policy
Multiple policies can be active simultaneously. They are evaluated in priority order.

​
Plan Limits

TierMax PoliciesPolicy Types
Starter3routing
Pro10routing, content
Growth25routing, content
Team50routing, content
Enterprise1000all types