> ## 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 Tab API — conversational answers, sources, places and products

> Ask Naver's AI Tab a question and get its answer as Markdown, with sources, places, products, images and videos.

`NAVER_AI_TAB` asks Naver's AI Tab, the always-on conversational answer on Naver search.

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

## Request

`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_TAB", "payload": { "query": "best running shoes for flat feet", "country": "KR" } }'
```

## Response

| Field | Type | Description |
| - | - | - |
| `text` | string | The answer. |
| `markdown` | string | The answer with Naver's cards written in place. Returned without any flag. |
| `sources` | array | `position`, `url`, `label`, `description`. |
| `map` | array | Places, for place questions: `name`, `position`, `placeId`, `location`, `url`, `mapsUrl`, `reviews`, `category`, `image`. |
| `products` | array | Products, for shopping questions. |
| `images` | array | Images shown with the answer: `title`, `url`, `image`, `thumbnail`, `source`, `sourceName`. |
| `videos` | array | Videos shown with the answer. |
| `rawContent` | string | The original event stream. Only with `include.rawResponse`. |

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

For example:

```json theme={"theme":"css-variables"}
{
  "text": "For flat feet, look for stability shoes with firm arch support ...",
  "markdown": "For flat feet, look for **stability shoes** with firm arch support [1].",
  "sources": [{ "position": 1, "url": "https://blog.naver.com/...", "label": "Running shoes for flat feet", "description": "..." }]
}
```

When Naver declines a query on policy grounds, the task completes with that refusal and a `notice` whose `type` is `policy_declined`.

## 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 answer. |

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


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