Perplexity Research API
Returns a written answer to a natural-language question researched over the live web, along with the source URLs the answer was built from.
GET /v1/perplexity/researchLast updated November 2026Maintained by the SocialCrawl team
When to use the Perplexity Research API
Use it for open questions that need current information, such as recent news or funding, rather than a fixed lookup on one platform.
From the API reference
Natural-language research over the live web powered by Perplexity Sonar. Returns a synthesised answer plus the URLs Sonar cited as evidence under data.sources. Costs 1 credit per call. Auto-refunds on upstream failure. Best for freeform questions like 'what is the latest funding round for Anthropic' or 'summarise this week's biggest LLM releases' that need fresh, web-grounded answers: the kind of question a structured social-media call cannot answer.
Searching 69 platforms in parallel
What can you do with the Research API?
The Research endpoint gives you structured Perplexity data with computed fields in a single request. No scraping infrastructure to build or maintain.
Example Request
# GET /v1/perplexity/research: 1 credit per call. Cache hits are free and failed calls are refunded.
# Check the price first for 0 credits: add dry_run=1 to the query. Nothing is fetched or charged.
# --max-time 16: this endpoint's measured p99 latency x 1.5.
# --retry 3: retries timeouts, 429 and 5xx, honoring Retry-After.
# -o response.json keeps only the final attempt's body.
# One Idempotency-Key per request, reused on every retry, so a retried call is never charged twice.
IDEMPOTENCY_KEY=$(od -An -N16 -tx1 /dev/urandom | tr -d ' \n')
curl -sS --max-time 16 --retry 3 -o response.json \
-H "x-api-key: YOUR_API_KEY" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
"https://www.socialcrawl.dev/v1/perplexity/research?query=What+is+the+capital+of+France%3F" && cat response.json# GET /v1/perplexity/research: 1 credit per call. Cache hits are free and failed calls are refunded.
# Check the price first for 0 credits: add dry_run=1 to the query. Nothing is fetched or charged.
import os
import random
import time
import uuid
import requests
API_KEY = os.environ.get("SOCIALCRAWL_API_KEY", "YOUR_API_KEY")
TIMEOUT_S = 16 # this endpoint's measured p99 latency x 1.5.
MAX_RETRIES = 3
URL = "https://www.socialcrawl.dev/v1/perplexity/research"
def backoff(attempt):
# Exponential backoff with jitter: about 1 s, 2 s, then 4 s.
return 2 ** attempt * (0.5 + random.random() / 2)
def socialcrawl(params):
# One Idempotency-Key per request, reused on every retry, so a retried call is never charged twice.
idempotency_key = str(uuid.uuid4())
for attempt in range(MAX_RETRIES + 1):
try:
res = requests.get(
URL,
params=params,
headers={"x-api-key": API_KEY, "Idempotency-Key": idempotency_key},
timeout=TIMEOUT_S,
)
body = res.json()
except (requests.RequestException, ValueError):
# A timeout, a dropped connection or a non-JSON gateway page: retry with the same key.
if attempt == MAX_RETRIES:
raise
time.sleep(backoff(attempt))
continue
if body["success"]:
return body
error = body["error"]
# Branch on error["type"], never on the message text.
if error["type"] == "RESOURCE_NOT_FOUND":
return None # refunded: nothing to read
retry_after = res.headers.get("Retry-After")
# SERVICE_UNAVAILABLE without Retry-After is a withdrawn endpoint: permanent.
permanent = error["type"] == "SERVICE_UNAVAILABLE" and retry_after is None
if not error.get("retryable") or permanent or attempt == MAX_RETRIES:
raise RuntimeError(f"{error['type']}: {error['message']} (request_id {body['request_id']})")
# Retry-After (seconds) wins; otherwise back off.
time.sleep(float(retry_after) if retry_after else backoff(attempt))
params = {
"query": "What is the capital of France?",
}
body = socialcrawl(params)
if body is not None:
print(body["data"])// GET /v1/perplexity/research: 1 credit per call. Cache hits are free and failed calls are refunded.
// Check the price first for 0 credits: add dry_run=1 to the query. Nothing is fetched or charged.
const API_KEY = process.env.SOCIALCRAWL_API_KEY ?? "YOUR_API_KEY";
const TIMEOUT_MS = 16_000; // this endpoint's measured p99 latency x 1.5.
const MAX_RETRIES = 3;
type Page = { next_cursor: string | null; has_more: boolean };
type SocialCrawlResponse =
| { success: true; data: any; pagination?: Page; credits_used: number; request_id: string }
| { success: false; error: { type: string; message: string; retryable: boolean }; request_id: string };
const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
// Exponential backoff with jitter: about 1 s, 2 s, then 4 s.
const backoffMs = (attempt: number) => 2 ** attempt * 1000 * (0.5 + Math.random() / 2);
async function socialcrawl(url: URL) {
// One Idempotency-Key per request, reused on every retry, so a retried call is never charged twice.
const idempotencyKey = crypto.randomUUID();
for (let attempt = 0; ; attempt++) {
let res: Response;
let body: SocialCrawlResponse;
try {
res = await fetch(url, {
headers: {
"x-api-key": API_KEY,
"Idempotency-Key": idempotencyKey,
},
signal: AbortSignal.timeout(TIMEOUT_MS),
});
body = (await res.json()) as SocialCrawlResponse;
} catch (error) {
// A timeout, a dropped connection or a non-JSON gateway page: retry with the same key.
if (attempt >= MAX_RETRIES) throw error;
await sleep(backoffMs(attempt));
continue;
}
if (body.success) return body;
// Branch on error.type, never on the message text.
if (body.error.type === "RESOURCE_NOT_FOUND") return null; // refunded: nothing to read
const retryAfter = res.headers.get("Retry-After");
// SERVICE_UNAVAILABLE without Retry-After is a withdrawn endpoint: permanent.
const permanent = body.error.type === "SERVICE_UNAVAILABLE" && retryAfter === null;
if (!body.error.retryable || permanent || attempt >= MAX_RETRIES) {
throw new Error(`${body.error.type}: ${body.error.message} (request_id ${body.request_id})`);
}
// Retry-After (seconds) wins; otherwise back off.
await sleep(retryAfter ? Number(retryAfter) * 1000 : backoffMs(attempt));
}
}
const url = new URL("https://www.socialcrawl.dev/v1/perplexity/research");
url.searchParams.set("query", "What is the capital of France?");
const body = await socialcrawl(url);
if (body) console.log(body.data);Parameters
| Parameter | Required | Description |
|---|---|---|
| query | Yes | Natural-language research prompt. Sonar autonomously searches the live web and grounds the response in real sources. No prompt-engineering required: phrase it as you would to a search engine or research assistant. |
What does the Perplexity Research API return?
This example shows the endpoint's response shape and fields. Values are illustrative; this is not a live capture.
Example response
{
"success": true,
"platform": "perplexity",
"endpoint": "/v1/perplexity/research",
"data": {
"answer": "Paris is the capital of France.",
"sources": [
{
"url": "https://en.wikipedia.org/wiki/Paris",
"title": "Paris - Wikipedia"
}
]
},
"credits_used": 1,
"credits_remaining": 99,
"request_id": "req-a1b2c3d4e5f6",
"cached": false
}Illustrative fixture for the documented response shape. Values are examples, not a production capture.
How does the Perplexity Research API work?
Send a GET request with your API key and get back clean, structured JSON in our unified schema. Supported computed fields are populated when the source provides the required inputs.
Method
GET
Response
JSON
How do you scrape social media data in seconds?
The fastest social media scraping API for developers. Scrape profiles, posts, comments, and analytics from 69 platforms covering 10B+ monthly active users.
One schema, every platform
Query 69 platforms with identical response structures. Write your integration once.
Computed fields, not just scraped
When an endpoint supports these metrics and the source provides the required inputs, the normalized record includes engagement_rate, estimated_reach, content_category, and language. Ready to use.
See your data before you code
Visual Data Explorer. Paste any URL, get rich result cards, sortable tables, CSV export.
import requests
response = requests.get(
'https://www.socialcrawl.dev/v1/tiktok/profile',
params={'handle': 'charlidamelio'},
headers={'x-api-key': 'sc_YOUR_API_KEY'}
)
data = response.json(){
"success": true,
"platform": "tiktok",
"data": {
"author": {
"username": "charlidamelio",
"followers": 152400000
},
"engagement": {
"likes": 12400000000,
"engagement_rate": 0.087
},
"metadata": {
"language": "en",
"content_category": "lifestyle"
}
}
}Have a question? We got answers
Find answers to frequently asked questions about SocialCrawl's API, pricing, and capabilities.
Contact usHow do I call the Perplexity Sonar API for research?
What does the research endpoint return?
Is this a Perplexity alternative or the real Perplexity?
How much does a research call cost?
Can I reach other AI search backends with the same key?
Ask AI about SocialCrawl
Ready to scrape Perplexity Research data?
Get your API key and start pulling Perplexity data in under 60 seconds.
