Naver AI Overview API
Returns the AI Briefing Naver shows for a query: the answer text, its blocks, the cited sources by number, and the media cards beside it.
GET /v1/naver/ai-overviewLast updated November 2026Maintained by the SocialCrawl team
When to use the Naver AI Overview API
Use it to see how Naver's AI answers a Korean query and which sources it cites.
From the API reference
Returns the AI Briefing Naver shows at the top of its results for a query. answer is the text, blocks keep Naver's layout (paragraphs, headings, lists with their items, tables as rows, the header row first) with the sources each block rests on, sources lists the cited pages by their number (index, url, title, site, snippet), the shape GET /v1/google/ai-overview answers in, and media the image and video cards Naver shows beside the answer. A query Naver shows no briefing for returns 404 and is not charged. An answer takes about 5 to 10 seconds.
95 platforms behind one API
What can you do with the AI Overview API?
The AI Overview endpoint gives you structured Naver data with computed fields in a single request. No scraping infrastructure to build or maintain.
Example Request
# GET /v1/naver/ai-overview: 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 60: the API's own time limit for this endpoint.
# --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 60 --retry 3 -o response.json \
-H "x-api-key: YOUR_API_KEY" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
"https://www.socialcrawl.dev/v1/naver/ai-overview?query=%EC%97%B4%ED%8E%8C%ED%94%84+%ED%9A%A8%EC%9C%A8" && cat response.json# GET /v1/naver/ai-overview: 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 = 60 # the API's own time limit for this endpoint.
MAX_RETRIES = 3
URL = "https://www.socialcrawl.dev/v1/naver/ai-overview"
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": "열펌프 효율",
}
body = socialcrawl(params)
if body is not None:
print(body["data"])// GET /v1/naver/ai-overview: 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 = 60_000; // the API's own time limit for this endpoint.
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/naver/ai-overview");
url.searchParams.set("query", "열펌프 효율");
const body = await socialcrawl(url);
if (body) console.log(body.data);Parameters
| Parameter | Required | Description |
|---|---|---|
| query | Yes | The search, up to 4,096 characters, Korean or any language, for example 열펌프 효율. |
What does the Naver AI Overview API return?
Every response follows one unified schema. Here is a real, unmodified response body, so you can see the exact fields you get back before spending a credit.
Example response
{
"success": true,
"platform": "instagram",
"endpoint": "/v1/instagram/engagement",
"data": {
"engagement_rate_percentages": 38.33,
"recent_posts": 12,
"followers": 87608035,
"comments": 528912,
"likes": 33049046,
"recent_posts_explanation": "Statistics based on the last 12 posts",
"id_user": "2278169415",
"username": "mrbeast",
"is_private": false,
"posts_details": [
{
"likes": 5636982,
"comments": 69484,
"taken_at": 1781457954,
"datetime": "2026-06-14 20:25:54",
"hours_since_post": 461,
"time_ago": "19 days ago",
"likes_per_hour": 12228,
"comments_per_hour": 151
},
{
"likes": 20000768,
"comments": 223510,
"taken_at": 1732824650,
"datetime": "2024-11-28 23:10:50",
"hours_since_post": 13971,
"time_ago": "2 years ago",
"likes_per_hour": 1432,
"comments_per_hour": 16
},
{
"likes": 929226,
"comments": 30633,
"taken_at": 1782232475,
"datetime": "2026-06-23 19:34:35",
"hours_since_post": 246,
"time_ago": "10 days ago",
"likes_per_hour": 3777,
"comments_per_hour": 125
},
{
"likes": 487761,
"comments": 22482,
"taken_at": 1781799425,
"datetime": "2026-06-18 19:17:05",
"hours_since_post": 366,
"time_ago": "15 days ago",
"likes_per_hour": 1333,
"comments_per_hour": 61
},
{
"likes": 712265,
"comments": 15716,
"taken_at": 1781366405,
"datetime": "2026-06-13 19:00:05",
"hours_since_post": 487,
"time_ago": "20 days ago",
"likes_per_hour": 1463,
"comments_per_hour": 32
},
{
"likes": 1475116,
"comments": 35386,
"taken_at": 1781277094,
"datetime": "2026-06-12 18:11:34",
"hours_since_post": 512,
"time_ago": "21 days ago",
"likes_per_hour": 2881,
"comments_per_hour": 69
},
{
"likes": 1108220,
"comments": 26632,
"taken_at": 1780160249,
"datetime": "2026-05-30 19:57:29",
"hours_since_post": 822,
"time_ago": "1 months ago",
"likes_per_hour": 1348,
"comments_per_hour": 32
},
{
"likes": 542948,
"comments": 28476,
"taken_at": 1779375582,
"datetime": "2026-05-21 17:59:42",
"hours_since_post": 1040,
"time_ago": "1 months ago",
"likes_per_hour": 522,
"comments_per_hour": 27
},
{
"likes": 698514,
"comments": 24401,
"taken_at": 1779120014,
"datetime": "2026-05-18 19:00:14",
"hours_since_post": 1111,
"time_ago": "2 months ago",
"likes_per_hour": 629,
"comments_per_hour": 22
},
{
"likes": 468000,
"comments": 13548,
"taken_at": 1778947209,
"datetime": "2026-05-16 19:00:09",
"hours_since_post": 1159,
"time_ago": "2 months ago",
"likes_per_hour": 404,
"comments_per_hour": 12
},
{
"likes": 526594,
"comments": 24411,
"taken_at": 1777737719,
"datetime": "2026-05-02 19:01:59",
"hours_since_post": 1495,
"time_ago": "2 months ago",
"likes_per_hour": 352,
"comments_per_hour": 16
},
{
"likes": 462652,
"comments": 14233,
"taken_at": 1777580305,
"datetime": "2026-04-30 23:18:25",
"hours_since_post": 1538,
"time_ago": "2 months ago",
"likes_per_hour": 301,
"comments_per_hour": 9
}
]
},
"credits_used": 5,
"credits_remaining": 9999,
"request_id": "req-8Kq2ZmR4vT9xLb3P",
"cached": false,
"redacted": true
}Example captured from the Instagram API. Every SocialCrawl endpoint returns this same unified schema, so your Naver AI Overview response has the same fields.
How does the Naver AI Overview 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 95 platforms covering 10B+ monthly active users.
One schema, every platform
Query 95 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 usWhat is the Naver AI Briefing API?
What shape is the answer?
What if Naver shows no briefing?
How long does an answer take?
How much does it cost?
Ask AI about SocialCrawl
Ready to scrape Naver AI Overview data?
Get your API key and start pulling Naver data in under 60 seconds.
