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

# Retrieving answers

> Retrieve answers with filters and cursor pagination, and understand the response structure

Retrieve collected answers with `GET /answers`. You can call it at any time, regardless of whether the run has finished, and it returns the answers collected so far.

## Retrieving answers

```bash theme={null}
curl -H "API-Key: YOUR_API_KEY" \
  "https://dev-platform-api.trychainshift.ai/api/v1/platform/answers?runID=0PCCDohFaNRcUWjLGoBGfw&model=CHATGPT&status=SUCCESS"
```

Below is a real collection response (the body is partially trimmed). The prompt is a Korean question asking for used SUV recommendations under 20M KRW.

```json theme={null}
{
  "answers": [
    {
      "id": "nyyblp5Yzq7gjZ3GKYopFw",
      "runID": "0PCCDohFaNRcUWjLGoBGfw",
      "promptID": "W-KMZMXwDB7ihFtj5CMHSQ",
      "query": "2000만원대 중고 SUV 추천해줘",
      "model": "CHATGPT",
      "region": "KR",
      "status": "SUCCESS",
      "content": "2000만원대 중고 SUV라면 “연식·크기·유지비” 균형을 보면 선택지가 꽤 좋습니다. 현재 시세 기준으로는 기아 셀토스, 현대 투싼, 기아 스포티지, 현대 싼타페 구형 세대 등이 많이 거론됩니다.\n제가 추천 순위를 매기면… (이하 생략)",
      "sources": [
        {
          "url": "https://car.ambitstock.com/domestic-suv-recommend-top7-segment-guide",
          "title": "국산 SUV 추천 TOP 7 — 2026년 가성비·연비·실내공간 세그먼트별 비교 | 모빌리티 인사이트",
          "domain": "ambitstock.com"
        },
        {
          "url": "https://car.ambitstock.com/mid-size-suv-recommend-top7-value-compare",
          "title": "중형 SUV 추천 TOP 7 — 3~5천만원대 국산·수입 가성비·연비·공간 완전 비교 (2026) | 모빌리티 인사이트",
          "domain": "ambitstock.com"
        }
      ],
      "fanouts": [
        "2026년 중고 SUV 2000만원대 추천 쏘렌토 싼타페 투싼 스포티지 시세"
      ],
      "markdownURL": "https://markdown-cdn.trychainshift.ai/a03e36ff-e99e-40d9-92d3-0784823f9b5b.md",
      "createdAt": "2026-07-28T06:27:40Z"
    }
  ],
  "nextCursor": "eyJpZCI6Njk0NTY5fQ"
}
```

This single response contains everything you need for AEO analysis: **what ChatGPT answered** (`content`), **which pages it cited as evidence** (`sources`, in this example two posts from a particular car blog), and **which search queries it actually issued** to build the answer (`fanouts`). Whether your site appears in the sources, and whether your content ranks for the fan-out queries, become your AEO action items.

### Filters

| Parameter | Description |
| - | - |
| `runID` | Only answers from a specific run request |
| `promptSetID` | Only answers from a specific prompt set |
| `promptID` | Only answers from a specific prompt |
| `model` | Only answers from a specific model (for example `CHATGPT`) |
| `region` | Only answers from a specific region (for example `KR`) |
| `location` | Only answers from a specific location (for example `US-NEW_YORK`) |
| `status` | `PENDING` / `SUCCESS` / `FAILED` |
| `from` / `to` | Creation time range (RFC3339, for example `2026-07-01T00:00:00Z`) |

## Pagination

All list endpoints use cursor pagination.

1. Send the first request without a `cursor`. Set the page size with `limit` (answers default to 20, maximum 100).
2. Pass the `nextCursor` value from the response as the `cursor` parameter of the next request, unchanged.
3. When `nextCursor` is `null`, you have reached the last page.

```bash theme={null}
curl -H "API-Key: YOUR_API_KEY" \
  "https://dev-platform-api.trychainshift.ai/api/v1/platform/answers?runID=0PCCDohFaNRcUWjLGoBGfw&limit=100&cursor=eyJpZCI6Njk0NTY5fQ"
```

> [!NOTE]
>
> If you change the filter conditions, clear the cursor and start again from
> the first page. Mixing a cursor issued under one set of conditions with
> different conditions produces inconsistent results.

## Understanding response fields

* `content`: the answer body text.
* `sources`: the list of sources the AI cited in the answer, with the URL, title, and domain of each. If you need the sentences actually quoted from a source, use `include=quotes` in [Cited URL ranking](https://dev-docs.trychainshift.ai/en/guides/analytics.md#cited-url-ranking).
* `fanouts`: the list of search queries the AI issued internally to build the answer. See the fan-out description in [Supported models](https://dev-docs.trychainshift.ai/en/models.md).
* `markdownURL`: URL of the raw answer as a markdown file.

> [!WARNING]
>
> `fanouts` and `sources` can be empty depending on the model and the answer.
> For when an empty value is expected behavior, see the empty-value rules in
> the [Answer object](https://dev-docs.trychainshift.ai/en/api-reference/answers/answer-object.md).

## Next steps

> [card] [Analyzing with statistics](https://dev-docs.trychainshift.ai/en/guides/analytics.md)
>
> Summarize answers with source domain and URL rankings and fan-out aggregation


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