Naver AI Mode
Query Naver's conversational AI Mode via Wire — the answer, its reasoning steps and cited sources
POST
https://api.anakin.io/v1/wire/taskNaver AI Mode is the conversational AI answer tab on Korea's top search portal — the multi-turn counterpart to Naver AI Briefing. Send a prompt and get the answer, the sources it cites (with where each is cited), and Naver's reasoning steps. Run it with the naver_ai_mode action on POST /v1/wire/task.
Catalog: naver · action_id: naver_ai_mode · Credits: 2 / call · Auth: none
Request Body
{
"action_id": "naver_ai_mode",
"params": { "prompt": "2026년 최고의 스마트폰", "country": "kr" }
}| Parameter | Type | Description |
|---|---|---|
action_id required | string | Set to naver_ai_mode |
params.prompt required | string | Your question for Naver AI Mode, up to 2048 chars. Any language — answers come back in Korean |
params.country | string | Country to run the request from (2-letter). Default kr |
params.additional_prompt | string | Optional follow-up, asked as a second turn in the same session |
params.include_html | boolean | Also return the answer as HTML (Naver's rendering) under answer_html. Default false |
params.include_raw | boolean | Also return Naver's raw response stream under response_raw (~50–600 KB). Default false |
Code Examples
curl -X POST https://api.anakin.io/v1/wire/task \
-H "X-API-Key: your_api_key" \
-H "Content-Type: application/json" \
-d '{
"action_id": "naver_ai_mode",
"params": { "prompt": "2026년 최고의 스마트폰", "country": "kr" }
}'import requests
res = requests.post(
'https://api.anakin.io/v1/wire/task',
headers={'X-API-Key': 'your_api_key'},
json={'action_id': 'naver_ai_mode', 'params': {'prompt': '2026년 최고의 스마트폰', 'country': 'kr'}},
)
job_id = res.json()['job_id']const res = await fetch('https://api.anakin.io/v1/wire/task', {
method: 'POST',
headers: { 'X-API-Key': 'your_api_key', 'Content-Type': 'application/json' },
body: JSON.stringify({
action_id: 'naver_ai_mode',
params: { prompt: '2026년 최고의 스마트폰', country: 'kr' },
}),
});
const { job_id } = await res.json();Response
202 Accepted{ "status": "processing", "job_id": "…", "poll_url": "/v1/wire/jobs/…" }Poll GET /v1/wire/jobs/{id} until status: "completed":
{
"status": "completed",
"credits_used": 2,
"data": {
"status": "ok",
"data": {
"answer_text": "…", "answer_text_markdown": "…", "answer_text_raw": "…",
"citations": [{ "url": "https://…", "title": "…" }],
"citation_anchors": [
{ "text": "…", "label": "…", "offset": 0, "urls": ["https://…"],
"source_ranks": [1], "chip_type": "…" }
],
"reasoning_steps": [], "search_sources": [],
"products": [], "businesses": [], "multimedia": [],
"conversation_id": "…", "turn": 1, "engine": "naver_ai_mode", "model": "naver_ai_tab"
},
"meta": { "action_id": "naver_ai_mode", "catalog_slug": "naver", "envelope_version": "v1" }
}
}| Field | Type | Description |
|---|---|---|
data.data.answer_text | string | The answer (also answer_text_markdown, and answer_html when include_html) |
data.data.additional_answer_text | string | The answer to additional_prompt, when you send one (also additional_answer_markdown, plus that turn's additional_citations) |
data.data.answer_text_raw | string | The raw, unprocessed answer — keeps Naver AI Mode's inline citation-chip labels and placeholder tokens that answer_text strips out |
data.data.follow_up_text | string | null | The reader-addressed closing/follow-up questions, split out of answer_text |
data.data.refused | boolean | Whether Naver AI Mode declined to answer |
data.data.refusal_text | string | The decline message when refused is true |
data.data.citations | array | Sources cited in the answer |
data.data.ads | null | Reserved — always null; Naver AI Mode shows no sponsored results |
data.data.citation_anchors | array | Where each source is cited in the answer — one entry per citation chip: the chip text/label, its offset in answer_text, the urls it groups and their source_ranks |
data.data.links_attached | array | The cited sources as a flat list in reading order: { url, text, position } |
data.data.references | array | The cited sources in { url, title, attribution, domain } shape |
data.data.search_sources | array | Sources Naver AI Mode considered during its web search (not necessarily cited) |
data.data.web_search_triggered | boolean | Whether Naver AI Mode actually ran a web search for this answer |
data.data.reasoning_steps | array | The reasoning/thinking steps Naver AI Mode shows before answering |
data.data.real_estate | array | Real-estate listing cards (Korea-specific module) |
data.data.businesses | array | Local business results |
data.data.products | array | Shopping/product modules for commercial-intent queries |
data.data.multimedia | array | Image/video cards attached to the answer |
data.data.conversation_id | string | Reuse to continue the thread (multi-turn) |
data.data.turn | integer | The conversation turn number |
data.data.response_raw | string | Naver AI Mode's raw response stream, verbatim. Not a stable contract — its format can change without notice; use the structured fields instead |
Naver AI Mode is the conversational surface; for the AI Briefing shown on the results page use
naver_prompt. Strongest on Korean-language, Korea-geo queries. Billed only on success.