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

# LLM Top Sources

> Rank the domains or pages that AI answers cite most for a topic, by mentions and AI search volume.

# LLM Top Sources

Which sites does AI quote when people ask about your category? Give a keyword such as `crm software`, or a domain, and get the top ten domains or individual pages cited across the matching AI answers, ranked by how many answers cite them. The page view is a ready shortlist for digital PR and content outreach: these are the articles worth getting your product into.

```json theme={"dark"}
{
  "query": "crm software",
  "platform": "google",
  "content_type": "domains"
}
```

Provide a keyword in query or a domain in target, not both. content\_type is domains (the default) or pages. platform is google (the default) or chat\_gpt (tracked for the United States in English). results\_limit defaults to 10, which is also the maximum. Each request costs 40 credits plus 0.5 credits per ranked domain or page; the 40 credits also apply when nothing is found.

## Standard Result Fields

Task results use the stable SocQ fields below. Source-specific field names and formats are normalized without inferring or enriching values that the source did not provide. To request a smaller field set, use `fields` for MCP queries, `_result_fields` for typed tools, or `--result-fields` in the CLI. Declared fields remain present when their value is `null`.

| Field | Type | Nullable | Description |
| - | - | - | - |
| `id` | `string` | Yes | Dimension and name, such as `source_domain:www.hubspot.com`. |
| `platform` | `string` | No | Platform the result belongs to, such as `instagram` or `linkedin`. |
| `resource` | `string` | No | SocQ resource represented by the result, such as `videos` or `comments`. |
| `type` | `string` | No | Category of the result item, such as `video`, `post`, or `comment`. |
| `url` | `string` | Yes | Homepage of the domain, or the page URL, when the row is a domain or page. |
| `published_at` | `string` | Yes | Time the source item was published, in ISO 8601 format when available. |
| `collected_at` | `string` | No | Time SocQ collected or processed this result, in ISO 8601 format. |
| `dimension` | `string` | Yes | What the row counts: `total`, `source_domain`, `search_result_domain`, `brand`, `brand_category`, `domain` or `page`. |
| `name` | `string` | Yes | Domain, page URL, brand or category the row counts; for `total`, the AI platform. |
| `rank` | `integer` | Yes | Position within its dimension, by mentions, starting at 1. |
| `mentions_count` | `integer` | Yes | Number of AI answers that mention or cite it. |
| `ai_search_volume` | `integer` | Yes | Combined monthly AI search volume of those answers' questions. |
| `ai_platform` | `string` | Yes | AI platform the answers come from: `google` or `chat_gpt`. |
| `target` | `string` | Yes | Domain that was tracked, when the request used target. |
| `query` | `string` | Yes | Keyword that was tracked, when the request used query. |

The following example shows the response format for a completed task. Actual data depends on your query.

## Completed Task Response

```json theme={"dark"}
{
  "code": 200,
  "data": {
    "task_id": "example-seo-llm-top-mentioned",
    "status": "succeeded",
    "public_id": "ai-search/llm-top-mentioned",
    "result_count": 1,
    "credits_amount": 40.5,
    "results": {
      "limit": 50,
      "next_cursor": null,
      "has_more": false,
      "schema_id": "llm-metric",
      "schema_version": "1.0",
      "items": [
        {
          "id": "page:https://www.salesforce.com/crm/what-is-crm/",
          "platform": "ai-search",
          "resource": "llm-top-mentioned",
          "type": "llm-metric",
          "url": "https://www.salesforce.com/crm/what-is-crm/",
          "published_at": null,
          "collected_at": "2026-11-17T23:54:13.890647Z",
          "dimension": "page",
          "name": "https://www.salesforce.com/crm/what-is-crm/",
          "rank": 1,
          "mentions_count": 716,
          "ai_search_volume": 3671360,
          "ai_platform": "google",
          "target": null,
          "query": "crm software"
        }
      ]
    }
  }
}
```


## OpenAPI

````yaml api-manual/agent-api/agent-api.json POST /v1/ai-search/llm-top-mentioned
openapi: 3.1.0
info:
  title: SocQ Agent API
  version: v1-87892a6484c2
  description: Asynchronous social data API generated from the SocQ Capability Registry.
servers:
  - url: https://api.socq.ai
security: []
paths:
  /v1/ai-search/llm-top-mentioned:
    post:
      tags:
        - ai-search
      summary: LLM Top Sources API
      description: Rank the domains and pages AI answers cite most for a topic.
      operationId: socq_ai_search_llm_top_mentioned
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $schema: https://json-schema.org/draft/2020-12/schema
              type: object
              additionalProperties: false
              properties:
                callback_url:
                  type: string
                  format: uri
                content_type:
                  type: string
                  minLength: 1
                  enum:
                    - domains
                    - pages
                  default: domains
                  description: Rank whole domains (domains) or single pages (pages).
                language:
                  type: string
                  minLength: 1
                language_code:
                  type: string
                  minLength: 2
                  maxLength: 10
                location_code:
                  type: integer
                  minimum: 1
                  description: Search market location code.
                location_name:
                  type: string
                  minLength: 1
                  description: Search market location name.
                platform:
                  type: string
                  minLength: 1
                  enum:
                    - chat_gpt
                    - google
                  default: google
                  description: >-
                    AI answers to read: google (AI Overviews) or chat_gpt
                    (ChatGPT, tracked for the United States in English).
                query:
                  type: string
                  minLength: 1
                  description: >-
                    Keyword or brand name to track in AI answers, such as crm
                    software. Give either target or query.
                results_limit:
                  type: integer
                  minimum: 1
                  maximum: 10
                  default: 10
                target:
                  type: string
                  minLength: 1
                  description: >-
                    Domain to track in AI answers, such as hubspot.com. Give
                    either target or query.
              required: []
              description: >-
                Provide a domain in target or a keyword in query. Rows rank the
                domains or pages that AI answers on the topic cite most, by
                mentions, with their AI search volume. results_limit defaults to
                10, the maximum.
              anyOf:
                - required:
                    - query
                - required:
                    - target
              allOf:
                - not:
                    required:
                      - query
                      - target
      responses:
        '200':
          description: Task accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgentSubmitResponse'
        '422':
          description: Input validation failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgentValidationErrorResponse'
      security:
        - bearerAuth: []
        - apiKeyAuth: []
components:
  schemas:
    AgentSubmitResponse:
      type: object
      properties:
        code:
          type: integer
          const: 200
        data:
          type: object
          properties:
            task_id:
              type: string
            status:
              type: string
            created_time:
              type:
                - string
                - 'null'
          required:
            - task_id
            - status
    AgentValidationErrorResponse:
      type: object
      properties:
        code:
          type: integer
          const: 422
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            details:
              type: object
          required:
            - message
            - type
      required:
        - code
        - error
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key

````

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