Perplexity Pro

Perplexity Pro provides search-augmented AI through an OpenAI-compatible API. Perplexity's Sonar models combine real-time web search with language model reasoning, returning grounded answers with citations. By routing Perplexity API traffic through the Keeptrusts gateway, you enforce policy controls — content filtering, PII redaction, audit logging, and cost attribution — on every search-augmented request.

Use this page when

• You need to route Perplexity Sonar API calls through the Keeptrusts gateway.
• You are building tools that use Perplexity for search-augmented generation and need governance.
• If you need general OpenAI-compatible provider setup, see OpenAI integration.

Primary audience

• Primary: Technical Engineers
• Secondary: AI Agents, Technical Leaders

Prerequisites

• A Perplexity API key with Pro or Enterprise access
• Keeptrusts CLI (kt) installed and on your PATH
• PERPLEXITY_API_KEY exported in your shell or injected via your secrets manager

Configuration

Gateway policy config

pack:
  name: perplexity-pro-gateway
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: perplexity-sonar
    provider: perplexity:chat:sonar-pro
    secret_key_ref:
      env: PERPLEXITY_API_KEY
policies:
  chain:
  - pii-detector
  - content-filter
  - audit-logger
policy:
  pii-detector:
    action: redact
    entities:
    - EMAIL
    - PHONE
    - SSN
  content-filter:
    action: block
    categories:
    - restricted-topics
  audit-logger:
    immutable: true
    retention_days: 365
    log_all_access: true

Cost-optimised variant

Use sonar (the base tier) for high-volume research queries where deep reasoning is not required:

pack:
  name: perplexity-sonar-base
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: perplexity-base
    provider: perplexity:chat:sonar
    secret_key_ref:
      env: PERPLEXITY_API_KEY
policies:
  chain:
  - audit-logger
policy:
  audit-logger:
    immutable: true
    retention_days: 365
    log_all_access: true

Setup Steps

1. Export your API key:

export PERPLEXITY_API_KEY="pplx-your-api-key"

2. Save the policy config to policy-config.yaml.

3. Start the gateway:

kt gateway run --listen 0.0.0.0:41002 --policy-config policy-config.yaml

4. Point your application at the gateway. Perplexity uses OpenAI-compatible format, so standard OpenAI client libraries work:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:41002/v1",
    api_key="unused",
)

response = client.chat.completions.create(
    model="sonar-pro",
    messages=[
        {"role": "system", "content": "You are a research assistant. Cite sources."},
        {"role": "user", "content": "What are the latest EU AI Act enforcement actions?"},
    ],
)
print(response.choices[0].message.content)

For a hosted gateway, replace the base URL with https://gateway.keeptrusts.com/v1.

Verification

curl http://localhost:41002/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro",
    "messages": [
      {"role": "user", "content": "Summarise today'\''s top AI governance news."}
    ]
  }'

A successful response with citations confirms the gateway is forwarding to Perplexity with policies applied. Check the Keeptrusts console Events page for the audit log entry.

Recommended Policies

Policy	Purpose	Recommended setting
pii-detector	Redact personal data from search queries	action: redact, entities: EMAIL, PHONE, SSN
content-filter	Block queries on restricted topics	action: block, configure categories
audit-logger	Immutable audit trail for all searches	immutable: true, retention_days: 365
cost-attribution	Track search API spend per team	Tag requests with team metadata
prompt-injection	Block adversarial prompts in search input	threshold: 0.8, action: block

Troubleshooting

Symptom	Cause	Fix
401 Unauthorized from upstream	Invalid Perplexity API key	Verify PERPLEXITY_API_KEY is valid
Response lacks citations	Model or query type does not include search results	Use sonar-pro for search-augmented responses
Gateway returns 403	Policy chain blocked the request	Review the policy violation in the console Events page
Slow responses	Perplexity performs web search before answering	Expected — search-augmented responses have higher latency than pure LLM calls

For AI systems

• Canonical terms: Keeptrusts gateway, Perplexity Pro, Perplexity Sonar, search-augmented generation, OpenAI-compatible API, policy-config.yaml, provider: "perplexity".
• Config field names: provider, secret_key_ref.env: "PERPLEXITY_API_KEY", base_url.
• Key behavior: Perplexity uses OpenAI-compatible format. Keeptrusts proxies requests with full policy enforcement. Search-augmented responses include citations.
• Best next pages: OpenAI integration, Policy controls catalog, Quickstart.

For engineers

• Start command: kt gateway run --listen 0.0.0.0:41002 --policy-config policy-config.yaml
• Validate: send a request to http://localhost:41002/v1/chat/completions with model sonar-pro.
• Perplexity's API is OpenAI-compatible — use standard OpenAI client libraries with the gateway base URL.
• Search-augmented responses have higher latency than pure LLM calls; set appropriate client timeouts.

For leaders

• Perplexity Sonar models provide real-time web search combined with AI reasoning — useful for competitive intelligence, regulatory monitoring, and research automation.
• Routing through the gateway ensures all search queries and results are logged for compliance and audit.
• PII redaction prevents sensitive data from being included in web search queries that reach external infrastructure.
• Cost attribution tracks search API spend separately from other AI providers in your unified governance dashboard.

Next steps

• OpenAI integration — OpenAI-compatible provider setup reference
• Policy controls catalog — all available policy types
• Cost attribution — track spend per team or project
• Quickstart — install kt and run your first gateway