Configure Perplexity enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for Perplexity. Trigger with phrases like "perplexity SSO", "perplexity RBAC", "perplexity enterprise", "perplexity roles", "perplexity permissions", "perplexity SAML".
From perplexity-packnpx claudepluginhub nickloveinvesting/nick-love-plugins --plugin perplexity-packThis skill is limited to using the following tools:
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Manage access to Perplexity's AI search API through API key scoping and per-query cost controls. Perplexity charges per query with pricing varying by model -- sonar (lightweight) costs less per query than sonar-pro (deeper research).
set -euo pipefail
# Key for the support bot (lightweight model only, low cost)
curl -X POST https://api.perplexity.ai/v1/api-keys \
-H "Authorization: Bearer $PPLX_ADMIN_KEY" \
-d '{
"name": "support-bot-prod",
"allowed_models": ["sonar"],
"rate_limit_rpm": 100,
"monthly_budget_usd": 200 # HTTP 200 OK
}'
# Key for the research team (full model access)
curl -X POST https://api.perplexity.ai/v1/api-keys \
-H "Authorization: Bearer $PPLX_ADMIN_KEY" \
-d '{
"name": "research-team",
"allowed_models": ["sonar", "sonar-pro"],
"rate_limit_rpm": 60,
"monthly_budget_usd": 1000 # 1000: 1 second in ms
}'
// pplx-gateway.ts - Route queries to appropriate model by team
const TEAM_CONFIG: Record<string, { model: string; maxTokens: number }> = {
support: { model: 'sonar', maxTokens: 512 }, # 512 bytes
sales: { model: 'sonar', maxTokens: 1024 }, # 1024: 1 KB
research: { model: 'sonar-pro', maxTokens: 4096 }, # 4096: 4 KB
};
function getModelForTeam(team: string): { model: string; maxTokens: number } {
return TEAM_CONFIG[team] || TEAM_CONFIG.support;
}
set -euo pipefail
# Restrict search to approved sources for compliance
curl -X POST https://api.perplexity.ai/chat/completions \
-H "Authorization: Bearer $PPLX_API_KEY" \
-d '{
"model": "sonar",
"messages": [{"role": "user", "content": "latest SEC filing for AAPL"}],
"search_domain_filter": ["sec.gov", "edgar.sec.gov"],
"return_citations": true
}'
set -euo pipefail
# Check API usage by key
curl https://api.perplexity.ai/v1/usage \
-H "Authorization: Bearer $PPLX_ADMIN_KEY" | \
jq '.keys[] | {name, queries_today, cost_today_usd, budget_remaining}'
Rotate API keys every 90 days. Label keys with creation date (research-team-2026Q1) for easy tracking. Create new key, deploy, then delete old key after 24-hour overlap.
| Issue | Cause | Solution |
|---|---|---|
401 invalid_api_key | Key revoked or expired | Generate new key |
403 model_not_allowed | Key restricted from sonar-pro | Use sonar or request broader key |
429 rate_limited | RPM cap exceeded | Add backoff or increase rate limit |
| Budget cap reached | Monthly spend exhausted | Increase budget or wait for cycle reset |
Basic usage: Apply perplexity enterprise rbac to a standard project setup with default configuration options.
Advanced scenario: Customize perplexity enterprise rbac for production environments with multiple constraints and team-specific requirements.