Perplexity is the most citation-forward AI engine — every claim links out. cloro returns its numbered source rail, inline citation pills, related queries, and the internal sub-queries it ran (with engine metadata) as structured JSON. Measure your citation share on the engine where citations are the product.
4.8 · 33 reviews
Sources, citation pills, related queries, and search_model_queries are all included in the base request — no add-on flags.
import requests
response = requests.post(
"https://api.cloro.dev/v1/monitor/perplexity",
headers={
"Authorization": "Bearer sk_live_your_api_key_here",
"Content-Type": "application/json"
},
json={
"prompt": "best email marketing platform for ecommerce",
"country": "US"
}
)
print(response.json()){
"success": true,
"result": {
"text": "For ecommerce, the platforms most often recommended are...",
"sources": [
{
"position": 1,
"url": "https://example.com/email-marketing-review",
"label": "Email Marketing Platforms Compared",
"description": "12 platforms tested on deliverability and automation"
}
],
"citationPills": [
{
"label": "Email Marketing Platforms Compared",
"citationPillId": 1,
"url": "https://example.com/email-marketing-review",
"domain": "example.com",
"position": 1
}
],
"related_queries": [
"klaviyo vs mailchimp for shopify",
"email marketing pricing comparison"
],
"search_model_queries": [
{
"query": "best email marketing platform ecommerce 2026",
"engine": "search"
}
]
}
} | Field | Type | Description |
|---|---|---|
| sources[].position | number | Position index of the source in the rail (the number users see). |
| sources[].url / label / description | string | Cited URL, display label, and source description. |
| citationPills[].citationPillId | integer | 1-based identifier shared by all entries from the same inline chip — group by it to reconstruct pills. |
| citationPills[].position | integer | 1-based pointer to the matching entry in result.sources. |
| citationPills[].domain | string | Host extracted from the URL, for grouping and display. |
| related_queries | string[] | Follow-up query suggestions Perplexity surfaces under the answer. |
| search_model_queries | object[] | Internal sub-queries Perplexity ran, with engine and limit metadata — its query fan-out. |
Pick a plan that fits your volume. Price per credit drops as you scale.
Increased concurrency, overages on credits and credit discounts for annual contracts.
Know moreCredit cost per request varies by provider. The rates below apply to async/batch requests; sync requests add a +2 credit surcharge.
ChatGPT full response includes query fan-out, ads, and shopping data. Google News uses the same pricing as Google Search.
Perplexity's whole UX is built on citations — users click through to sources at far higher rates than on other AI engines. A position-1 citation on a commercial prompt is real referral traffic, not just brand exposure, so citation share here converts most directly.
The sub-queries Perplexity decomposed your prompt into before retrieval — its query fan-out, with the engine each ran against. Rank for those intermediate queries and you enter the retrieval set for the prompt itself.
sources is the rail — the numbered list of consulted pages. citationPills are the inline chips inside the answer text; each carries a citationPillId (grouping entries from one chip) and a position pointing back into sources. Pills show which sources actually back specific claims.
Base requests are 3 credits with sources, citation pills, related queries, fan-out, and markdown all included. US `state` targeting adds +2. See pricing for the full table.
The Sonar API is a developer product with its own retrieval behavior — its answers and citation sets diverge from the consumer product your buyers use. cloro samples the real perplexity.ai surface, including UI-only elements like shopping cards, videos, and places.
Run your prompt set on a schedule per country, then aggregate cited domains by position. Our AI visibility tracking guide covers the methodology — the same pipeline works across ChatGPT, Gemini, and Copilot.