> ## Documentation Index
> Fetch the complete documentation index at: https://docs.querying.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Naver AI Brief API — AI briefing, sources and web results

> Search Naver and get the AI Brief summary box with its sources, related questions and the web documents beneath it.

`NAVER_AI_BRIEF` searches Naver and returns the AI Brief, the AI summary box on Naver's results page, together with the web documents shown beneath it.

| | |
| - | - |
| taskType | `NAVER_AI_BRIEF` |
| Aliases | `NAVER` (deprecated) |
| Reads | `query` (falls back to `prompt`) |
| Credits | 1.25 |
| Country | Optional, default **`KR`**. |

## Request

Naver is a Korean search engine, so `country` defaults to `KR` when you leave it out. The example below sends it explicitly.

```bash theme={"theme":"css-variables"}
curl -X POST https://api.querying.ai/v1/async/task \
  -H "Authorization: Bearer $QUERYING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskType": "NAVER_AI_BRIEF", "payload": { "query": "best running shoes for flat feet", "country": "KR" } }'
```

## Response

| Field | Type | Description |
| - | - | - |
| `text` | string | The briefing as plain text. Empty when Naver showed no briefing. |
| `markdown` | string | The briefing as Naver wrote it, with headings, lists and tables. Returned without any flag. |
| `sources` | array | `position`, `url`, `label`, `description`. |
| `relatedQuestions` | string\[] | Follow-up questions Naver suggests. |
| `images` | array | Images shown with the answer: `title`, `url`, `image`, `thumbnail`, `source`, `sourceName`. |
| `organicResults` | array | The web documents under the briefing box: `position`, `title`, `link`, `displayedLink`, `snippet`, `date`, `page`. |
| `rawContent` | string | The original event stream. Only with `include.rawResponse`. |

In `markdown`, citations appear as `[n]` on `sources[].position` and images as `![title](url)`.

The briefing is conditional: Naver does not show one for every query, and a task with no briefing still completes. The briefing and the documents come from two separate Naver requests. When Naver finds no documents, `organicResults` is absent rather than empty. If either request cannot be read, the task fails with `ENGINE_NO_RESULT`.

For example:

```json theme={"theme":"css-variables"}
{
  "text": "Shoes with firm arch support and a stable midsole suit flat feet ...",
  "markdown": "### Choosing shoes for flat feet\n- Firm arch support [1]\n- Stable midsole [2]",
  "sources": [{ "position": 1, "url": "https://blog.naver.com/...", "label": "Running shoes for flat feet", "description": "..." }],
  "relatedQuestions": ["Which brands make stability running shoes?"],
  "organicResults": [
    { "position": 1, "title": "Stability running shoes guide", "link": "https://www.example.com/guide", "displayedLink": "example.com", "snippet": "...", "page": 1 }
  ]
}
```

## Include flags

| Flag | Effect |
| - | - |
| `rawResponse` | Adds `rawContent`. |
| `analysis` | Adds `analysis`, 1 credit. See [Answer analysis](/engines/answer-analysis.md). |
| `citationAnalysis` | Runs a [Citation Analysis](/research/citation-analysis.md) on the briefing. |

`markdown` needs no flag. `searchQueries`, `ads` and `shopping` have no effect. `html` is rejected with `422 EVIDENCE_UNSUPPORTED`. See [Markdown and raw responses](/engines/response-options.md).

## Related

* [Naver AI Brief product page](https://querying.ai/en/engines/naver-ai-brief)
* [Naver AI Tab](/engines/naver-ai-tab.md)
* [Naver Search](/engines/naver-serp.md)
* [Engine overview](/engines/overview.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.