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

# Read mention statements — HTTP

> Retrieve answer statements that mention selected brand terms.

Retrieve answer statements that mention selected brand terms.

**Method:** `GET`

**Path:** `/projects/{project_id}/runs/{run_id}/mention-statements`

Use the HTTP base for your authorized environment and an `Authorization: Bearer` header. See [authentication](/developers/guides/04-authentication) and [HTTP setup](/developers/guides/06-http-quickstart).

## Parameters

This table covers the standard read profile. It excludes internal application routes and advanced analysis controls.

| Name | Location | Type | Required | Default | Meaning |
| - | - | - | - | - | - |
| `project_id` | path | string | Yes | — | Project ID from list\_projects. Select the project in the intended workspace and environment. |
| `run_id` | path | string | Yes | — | Run ID from list\_runs for this project. Use the exact returned value and check readiness before reading measurements. |
| `entities` | query | string | No | `null` | JSON-encoded array. Measured names to include. Multiple names select statements mentioning any listed name; they do not require every name in one statement. |
| `include_ungrounded` | query | boolean | No | `true` | Include brand statements that have no citation support. False restricts results to grounded statements. |
| `include_full_response` | query | boolean | No | `false` | Include the answer containing the statement, subject to max\_text\_chars. |
| `max_text_chars` | query | integer | No | `500` | Character limit applied to returned statement text and, when requested, full response text. Shortened text is not the complete evidence. Minimum 50. Maximum 2000. |
| `limit` | query | integer | No | `25` | Maximum statement rows on this page. Continue with data.cursor when supplied. Minimum 1. Maximum 100. |
| `cursor` | query | string | No | `null` | Next-page value from data.cursor. Keep the project, run, filters, and text settings unchanged when continuing. |
| `filters` | query | string | No | `null` | JSON-encoded array. Select measured answers with objects containing dimension and values. Use labels from list\_dimension\_options; inspect returned warnings for filters that were not applied. |
| `prompt_type` | query | string | No | `null` | Select an exact Category facet label returned for the project. |
| `intent` | query | string | No | `null` | Select an exact Customer Intent facet label returned for the project. |
| `topic` | query | string | No | `null` | Select an exact measured topic label. A broader phrase does not select every topic containing that phrase. |
| `query_id` | query | integer | No | `null` | Restrict evidence to one integer query ID returned by list\_queries. |

## Request example

Set `IQRUSH_API_BASE` and `IQRUSH_ACCESS_TOKEN` through secure configuration. Replace project/run IDs and sample selections with values returned by your account. JSON objects and arrays are encoded as query strings.

```bash theme={null}
curl --fail-with-body --silent --show-error --get \
  --header "Authorization: Bearer ${IQRUSH_ACCESS_TOKEN}" \
  --header "Accept: application/json" \
  --data-urlencode 'entities=["Colorescience"]' \
  --data-urlencode include_full_response=false \
  --data-urlencode limit=25 \
  "${IQRUSH_API_BASE%/}/projects/${IQRUSH_PROJECT_ID}/runs/${IQRUSH_RUN_ID}/mention-statements"
```

## Read the response

Measurement `data.rows` contains statement evidence and source information. Use `data.cursor` for the next page; keep the same filters and text settings.

Several requested entities means ANY of them, not all together. A statement can contain multiple sentences. Text can be shortened by `max_text_chars`, including when full response text is requested.

### Fields to use

These selected fields explain the example and the result to preserve. Field presence depends on the response; this is not a complete response schema.

| Field | Meaning and use |
| - | - |
| `data.rows[].platform` | Platform associated with the statement. |
| `data.rows[].mentioned_terms` | Measured names identified in the statement. |
| `data.rows[].is_grounded` | Whether the statement has recorded citation support. |
| `data.rows[].grounding_urls` | URLs recorded as supporting the statement; an empty list has no URLs to cite as evidence. |
| `data.n_available` | Statement rows available after selection, before the page limit. |
| `data.cursor` | Opaque value to pass as `cursor` in the next request. A null or absent value means there is no next page. |

Selected response fields from IQRush Dev. Lists are shortened and project/run IDs are placeholders; this is not the full response.

```json theme={null}
{
  "data_ready": true,
  "data": {
    "rows": [
      {
        "platform": "OPENAI",
        "mentioned_terms": [
          "Colorescience"
        ],
        "is_grounded": false,
        "grounding_urls": []
      }
    ],
    "n_available": 280
  }
}
```

Text and record identifiers are omitted from this excerpt. Retrieve those fields from your own response when preparing an evidence review.

MCP equivalent: [`list_mention_statements`](/developers/tools/list_mention_statements). Use the parameters and defaults on this page for HTTP.

## If the result is unavailable

Check HTTP status and the response’s `error` field before using data. A successful empty response does not establish a zero value. Preserve `not_available`, `not_available_reason`, `unavailable_reason`, and `linked` where returned. [Errors and recovery](/developers/guides/13-errors) shows observed examples.


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