# LLM Brand Mentions API

How AI assistants answer your prompts and whether they mention your brand or competitors, with assistant, model, country and the full answer. Pass prompts, brand aliases, competitors and assistants.

**Pricing:** $0.006 per answer

**Endpoint:** `POST /v1/data/llm/brand-mentions/run`

**Auth:** `Authorization: Bearer mk_live_...`

## Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompts` | array | Yes | One or more prompts. One request reads them all. |
| `brand` | string | Yes | Brand. |
| `brandAliases` | array | No | One or more brand aliases. One request reads them all. |
| `brandWebsite` | string | No | Brand Website. |
| `competitors` | array | No | One or more competitors. One request reads them all. |
| `assistants` | array | No | Which AI assistants to ask: ChatGPT, Gemini, Google AI Mode, Google AI Overview. Each assistant gives one answer (one row) per prompt, so 3 prompts on 2 assistants is 6 answers. Defaults to ChatGPT. |
| `country` | string | No | Country the prompts are asked from, e.g. United Kingdom. Defaults to United States. |

## Example

`?wait=true` holds the request open until the run finishes (up to 60s) and returns the rows inline: one request, no polling.

```bash
curl -X POST "https://api.mindcase.co/v1/data/llm/brand-mentions/run?wait=true" \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"params":{"prompts":["..."],"brand":"..."}}'
```

```python
import requests

resp = requests.post(
    "https://api.mindcase.co/v1/data/llm/brand-mentions/run",
    params={"wait": "true"},
    headers={"Authorization": "Bearer mk_live_YOUR_API_KEY"},
    json={"params": {
    "prompts": [
        "..."
    ],
    "brand": "..."
}},
)
rows = resp.json()["data"]
```

## Longer runs

If the run is still going at the 60s ceiling you get back `{ job_id, status: "running" }` instead of rows (same if the result is over 100 rows; those come back `truncated`). Poll with that `job_id`:

```bash
# 1) check status
curl https://api.mindcase.co/v1/jobs/JOB_ID \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY"

# 2) when status == completed, fetch the rows
curl https://api.mindcase.co/v1/jobs/JOB_ID/results \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY"
```

Full API reference (auth, jobs, balance, SDKs, MCP): https://mindcase.co/skills.md

## Response columns

| Field | Display name | Type |
|-------|--------------|------|
| `prompt` | Prompt | text |
| `assistant` | Assistant | text |
| `model` | Model | text |
| `country` | Country | text |
| `answeredAt` | Answered At | date |
| `aiAnswer` | Ai Answer | text |
| `brand` | Brand | text |
| `brandMentioned` | Brand Mentioned | boolean |
| `brandPosition` | Brand Position | number |
| `brandCited` | Brand Cited | boolean |
| `brandCitedUrls` | Brand Cited URLs | array |
| `brandsNamed` | Brands Named | array |
| `competitorsNamed` | Competitors Named | array |
| `shareOfVoice` | Share Of Voice | number |
| `aiAnswerSources` | Ai Answer Sources | object_array |
| `sourcesCount` | Sources Count | number |
| `searchQueries` | Search Queries | array |
| `products` | Products | object_array |
| `rowId` | Row Id | text |