CrawlGraph REST API v1

openapi: 3.1.0
info:
  title: CrawlGraph
  description: Free backlink intelligence powered by Common Crawl's hyperlink graph.
  version: 1.2.0
  contact:
    name: CrawlGraph support
    email: petteri@searchenginewizards.fi
    url: https://crawlgraph.com/docs/api
  termsOfService: https://crawlgraph.com/terms
paths:
  /api/v1/backlinks:
    post:
      tags:
      - v1
      summary: Look up referring domains for a target domain
      description: 'Public-API backlink lookup.


        Validates ``domain`` and ``release_id`` (400 ``validation_error`` on

        failure), charges one call against the caller''s monthly

        ``backlinks`` quota (429 ``quota_exceeded`` on overflow), then runs

        the same DuckDB query the internal route uses and returns the

        sliced results.'
      operationId: v1_lookup_backlinks_api_v1_backlinks_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1BacklinksBody'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1BacklinksResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/free-key:
    post:
      tags:
      - v1
      summary: Request Free Key
      description: 'Request a free-tier API key (15 backlink calls per month; gap

        analysis requires the $99 lifetime tier). The key is emailed to the address you provide - it is
        never

        returned in this response. One active key per email. Lifetime

        customers manage keys at /account instead.'
      operationId: request_free_key_api_v1_free_key_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FreeKeyRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: object
                title: Response Request Free Key Api V1 Free Key Post
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security: []
  /api/v1/releases:
    get:
      tags:
      - v1
      summary: List available Common Crawl releases
      description: 'Return the list of releases the API can serve queries from.


        Does NOT charge against the caller''s quota.'
      operationId: v1_list_releases_api_v1_releases_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1ReleasesResponse'
  /api/v1/gap-analysis:
    post:
      tags:
      - v1
      summary: Submit an async gap-analysis job
      description: 'Queue a gap-analysis job and return a poll URL.


        Validates the input domains, charges one call against the caller''s

        monthly ``gap`` quota (429 ``quota_exceeded`` on overflow), creates

        a row in ``export_jobs`` (``kind="gap"``), and schedules the worker

        via FastAPI''s ``BackgroundTasks``. The poll endpoint reads the same

        table and is owner-scoped.'
      operationId: v1_gap_submit_api_v1_gap_analysis_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1GapBody'
        required: true
      responses:
        '202':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1GapSubmitResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/gap-analysis/{job_id}:
    get:
      tags:
      - v1
      summary: Poll a gap-analysis job
      description: 'Return the current status of a gap-analysis job.


        Owner-scoped - jobs that don''t exist or that belong to another user

        both return ``404 not_found`` (``get_job_for_user`` enforces the

        ownership check; we can''t distinguish the two cases, which is the

        point - never leak another user''s job ids).'
      operationId: v1_gap_poll_api_v1_gap_analysis__job_id__get
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          title: Job Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1GapStatusResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/changes:
    get:
      tags:
      - v1
      summary: Compare inbound-link observations across indexed releases
      description: Return observed additions, absences, and authority movement.
      operationId: v1_changes_api_v1_changes_get
      parameters:
      - name: domain
        in: query
        required: true
        schema:
          type: string
          maxLength: 253
          description: Target domain to compare.
          title: Domain
        description: Target domain to compare.
      - name: from
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            maxLength: 64
          - type: 'null'
          description: Older release id. Defaults to the older release in the newest queryable pair, or
            to an explicit 'to' release's nearest queryable ancestor.
          title: From
        description: Older release id. Defaults to the older release in the newest queryable pair, or
          to an explicit 'to' release's nearest queryable ancestor.
      - name: to
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            maxLength: 64
          - type: 'null'
          description: Newer release id. Defaults to the newer release in the newest queryable pair.
          title: To
        description: Newer release id. Defaults to the newer release in the newest queryable pair.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                anyOf:
                - $ref: '#/components/schemas/V1ChangesAvailableResponse'
                - $ref: '#/components/schemas/V1ChangesUnavailableResponse'
                title: Response V1 Changes Api V1 Changes Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    AttributionPayload:
      properties:
        utm_source:
          anyOf:
          - type: string
            maxLength: 64
          - type: 'null'
          title: Utm Source
        utm_medium:
          anyOf:
          - type: string
            maxLength: 64
          - type: 'null'
          title: Utm Medium
        utm_campaign:
          anyOf:
          - type: string
            maxLength: 64
          - type: 'null'
          title: Utm Campaign
        utm_content:
          anyOf:
          - type: string
            maxLength: 128
          - type: 'null'
          title: Utm Content
        utm_term:
          anyOf:
          - type: string
            maxLength: 128
          - type: 'null'
          title: Utm Term
        landing_path:
          anyOf:
          - type: string
            maxLength: 256
          - type: 'null'
          title: Landing Path
        referrer_host:
          anyOf:
          - type: string
            maxLength: 253
          - type: 'null'
          title: Referrer Host
      type: object
      title: AttributionPayload
    FreeKeyRequest:
      properties:
        email:
          type: string
          format: email
          title: Email
        attribution:
          anyOf:
          - $ref: '#/components/schemas/AttributionPayload'
          - type: 'null'
      type: object
      required:
      - email
      title: FreeKeyRequest
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    V1BacklinkItem:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
        num_hosts:
          type: integer
          title: Num Hosts
        tld:
          type: string
          title: Tld
        cg_authority:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Authority
        cg_rank:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Rank
      type: object
      required:
      - linking_domain
      - num_hosts
      - tld
      title: V1BacklinkItem
      description: 'One referring-domain row in the response.


        ``tld`` is the last label of ``linking_domain`` (no leading dot).

        ``cg_authority`` is a 0..100 log-rank percentile from the Common

        Crawl harmonic-centrality ranking (higher = more authoritative).

        ``cg_rank`` is the raw PageRank position across the whole graph

        (1 = top-ranked domain on the web). Both are NULL for domains

        that don''t appear in the ranks file.'
    V1BacklinksBody:
      properties:
        domain:
          type: string
          maxLength: 255
          minLength: 1
          title: Domain
          description: Target domain to look up backlinks for, e.g. 'example.com'.
        release_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Release Id
          description: Common Crawl release id. Defaults to the latest release.
        limit:
          type: integer
          maximum: 10000.0
          minimum: 1.0
          title: Limit
          description: Max number of result rows to return (1..10000).
          default: 1000
        sort:
          type: string
          enum:
          - authority
          - hosts
          title: Sort
          description: Result ordering. 'authority' (default) sorts by cg_authority DESC then num_hosts
            DESC. 'hosts' preserves the legacy num_hosts DESC ordering.
          default: authority
      type: object
      required:
      - domain
      title: V1BacklinksBody
      description: Request body for ``POST /api/v1/backlinks``.
    V1BacklinksResponse:
      properties:
        domain:
          type: string
          title: Domain
        release_id:
          type: string
          title: Release Id
        release_label:
          type: string
          title: Release Label
        total_linking_domains:
          type: integer
          title: Total Linking Domains
          description: Number of distinct linking domains retrieved before the `limit` slice was applied.
        returned:
          type: integer
          title: Returned
          description: Number of rows actually included in `results`.
        cg_authority:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Authority
          description: 0..100 log-rank percentile for the queried `domain`. NULL when the domain is missing
            from the ranks file.
        cg_rank:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Rank
          description: Raw PageRank position of the queried `domain` (1 = top). NULL when the domain is
            missing from the ranks file.
        results:
          items:
            $ref: '#/components/schemas/V1BacklinkItem'
          type: array
          title: Results
      type: object
      required:
      - domain
      - release_id
      - release_label
      - total_linking_domains
      - returned
      - results
      title: V1BacklinksResponse
      description: Top-level response body for ``POST /api/v1/backlinks``.
    V1ChangesAuthorityMovement:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
        from_authority:
          type: integer
          title: From Authority
        to_authority:
          type: integer
          title: To Authority
        delta:
          type: integer
          title: Delta
      type: object
      required:
      - linking_domain
      - from_authority
      - to_authority
      - delta
      title: V1ChangesAuthorityMovement
    V1ChangesAvailableResponse:
      properties:
        domain:
          type: string
          title: Domain
        to_release:
          $ref: '#/components/schemas/V1ChangesRelease'
        counts:
          $ref: '#/components/schemas/V1ChangesCounts'
        added:
          items:
            $ref: '#/components/schemas/V1ChangesObservedDomain'
          type: array
          title: Added
          description: Referring domains observed only in the newer snapshot.
        removed:
          items:
            $ref: '#/components/schemas/V1ChangesObservedDomain'
          type: array
          title: Removed
          description: Referring domains observed in the older snapshot but absent from the newer snapshot.
        authority_moved:
          items:
            $ref: '#/components/schemas/V1ChangesAuthorityMovement'
          type: array
          title: Authority Moved
        truncated:
          type: boolean
          title: Truncated
        cap:
          type: integer
          title: Cap
        snapshot_caveat:
          type: string
          title: Snapshot Caveat
        comparison_available:
          type: boolean
          enum:
          - true
          const: true
          title: Comparison Available
        from_release:
          $ref: '#/components/schemas/V1ChangesRelease'
      type: object
      required:
      - domain
      - to_release
      - counts
      - added
      - removed
      - authority_moved
      - truncated
      - cap
      - snapshot_caveat
      - comparison_available
      - from_release
      title: V1ChangesAvailableResponse
    V1ChangesCounts:
      properties:
        from_snapshot:
          type: integer
          title: From Snapshot
        to_snapshot:
          type: integer
          title: To Snapshot
        added:
          type: integer
          title: Added
          description: Referring domains observed only in the newer snapshot.
        removed:
          type: integer
          title: Removed
          description: Referring domains absent from the newer snapshot.
        authority_moved:
          type: integer
          title: Authority Moved
      type: object
      required:
      - from_snapshot
      - to_snapshot
      - added
      - removed
      - authority_moved
      title: V1ChangesCounts
    V1ChangesObservedDomain:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
        num_hosts:
          type: integer
          title: Num Hosts
        cg_authority:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Authority
      type: object
      required:
      - linking_domain
      - num_hosts
      title: V1ChangesObservedDomain
    V1ChangesRelease:
      properties:
        id:
          type: string
          title: Id
        label:
          type: string
          title: Label
      type: object
      required:
      - id
      - label
      title: V1ChangesRelease
    V1ChangesUnavailableResponse:
      properties:
        domain:
          type: string
          title: Domain
        to_release:
          $ref: '#/components/schemas/V1ChangesRelease'
        counts:
          $ref: '#/components/schemas/V1ChangesCounts'
        added:
          items:
            $ref: '#/components/schemas/V1ChangesObservedDomain'
          type: array
          title: Added
          description: Referring domains observed only in the newer snapshot.
        removed:
          items:
            $ref: '#/components/schemas/V1ChangesObservedDomain'
          type: array
          title: Removed
          description: Referring domains observed in the older snapshot but absent from the newer snapshot.
        authority_moved:
          items:
            $ref: '#/components/schemas/V1ChangesAuthorityMovement'
          type: array
          title: Authority Moved
        truncated:
          type: boolean
          title: Truncated
        cap:
          type: integer
          title: Cap
        snapshot_caveat:
          type: string
          title: Snapshot Caveat
        comparison_available:
          type: boolean
          enum:
          - false
          const: false
          title: Comparison Available
        from_release:
          anyOf:
          - $ref: '#/components/schemas/V1ChangesRelease'
          - type: 'null'
        message:
          type: string
          title: Message
      type: object
      required:
      - domain
      - to_release
      - counts
      - added
      - removed
      - authority_moved
      - truncated
      - cap
      - snapshot_caveat
      - comparison_available
      - from_release
      - message
      title: V1ChangesUnavailableResponse
    V1GapBody:
      properties:
        my_domain:
          type: string
          maxLength: 255
          minLength: 1
          title: My Domain
          description: Your domain (the one you want to find gaps for).
        competitor_domains:
          items:
            type: string
          type: array
          maxItems: 5
          minItems: 1
          title: Competitor Domains
          description: 1..5 competitor domains. Linking domains that link to any of these but not to ``my_domain``
            are returned as gaps.
      type: object
      required:
      - my_domain
      - competitor_domains
      title: V1GapBody
      description: Request body for ``POST /api/v1/gap-analysis``.
    V1GapResultBody:
      properties:
        my_domain:
          type: string
          title: My Domain
        competitor_domains:
          items:
            type: string
          type: array
          title: Competitor Domains
        gaps:
          items:
            $ref: '#/components/schemas/V1GapResultGap'
          type: array
          title: Gaps
        total_gaps:
          type: integer
          title: Total Gaps
          description: '``len(gaps)`` - convenience for clients.'
        truncated:
          type: boolean
          title: Truncated
          description: True when the result was clipped to the export cap (25,000 gaps); more linking
            domains exist than were returned.
          default: false
      type: object
      required:
      - my_domain
      - competitor_domains
      - gaps
      - total_gaps
      title: V1GapResultBody
      description: The ``result`` object on a completed job.
    V1GapResultGap:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
          description: Domain that links to one or more competitors but not to ``my_domain``.
        found_on:
          items:
            type: string
          type: array
          title: Found On
          description: Subset of the request's ``competitor_domains`` that this linking_domain points
            at.
      type: object
      required:
      - linking_domain
      - found_on
      title: V1GapResultGap
      description: One gap row in a completed job's result.
    V1GapStatusResponse:
      properties:
        job_id:
          type: string
          title: Job Id
        status:
          type: string
          title: Status
          description: One of "queued" | "running" | "completed" | "failed".
        progress_pct:
          anyOf:
          - type: integer
          - type: 'null'
          title: Progress Pct
          description: 0..100 progress hint while ``status == "running"``.
        started_at:
          anyOf:
          - type: string
          - type: 'null'
          title: Started At
          description: ISO 8601 timestamp; populated once the worker picks up the job.
        completed_at:
          anyOf:
          - type: string
          - type: 'null'
          title: Completed At
          description: ISO 8601 timestamp; populated when ``status == "completed"``.
        result:
          anyOf:
          - $ref: '#/components/schemas/V1GapResultBody'
          - type: 'null'
          description: Populated when ``status == "completed"``.
        error:
          anyOf:
          - type: object
          - type: 'null'
          title: Error
          description: 'Populated when ``status == "failed"``. Shape: ``{"code": "...", "message": "..."}``.'
      type: object
      required:
      - job_id
      - status
      title: V1GapStatusResponse
      description: '``GET /api/v1/gap-analysis/{job_id}`` response.


        Single model with optional fields rather than a discriminated union -

        consumers can branch on ``status`` and pick out the field set

        relevant to that state.'
    V1GapSubmitResponse:
      properties:
        job_id:
          type: string
          title: Job Id
        status:
          type: string
          title: Status
          description: Always ``"queued"`` on submit.
        poll_url:
          type: string
          title: Poll Url
          description: GET this URL to poll job status.
      type: object
      required:
      - job_id
      - status
      - poll_url
      title: V1GapSubmitResponse
      description: '``202`` response body when a job is queued.'
    V1ReleaseItem:
      properties:
        id:
          type: string
          title: Id
          description: Release identifier, e.g. 'cc-main-2026-jan-feb-mar'.
        label:
          type: string
          title: Label
          description: Human label for the release, e.g. 'Jan-Mar 2026'.
        available:
          type: boolean
          title: Available
          description: Whether manifest intent and the corresponding DuckDB artifact both allow queries
            for this release.
      type: object
      required:
      - id
      - label
      - available
      title: V1ReleaseItem
      description: One Common Crawl release the API can serve queries from.
    V1ReleasesResponse:
      properties:
        releases:
          items:
            $ref: '#/components/schemas/V1ReleaseItem'
          type: array
          title: Releases
      type: object
      required:
      - releases
      title: V1ReleasesResponse
      description: Top-level response body for ``GET /api/v1/releases``.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Bearer token. Keys are prefixed cg_live_ and are roughly 52 characters. Sent as `Authorization:
        Bearer cg_live_<key>`. Every /api/v1/* route requires it except POST /api/v1/free-key, which is
        unauthenticated. Documented at https://crawlgraph.com/docs/api section 2.'
servers:
- url: https://crawlgraph.com
  description: CrawlGraph production API (paths carry the /api/v1 prefix)
security:
- bearerAuth: []
tags:
- name: v1
  description: CrawlGraph public REST API v1 — backlink lookups, Common Crawl release discovery, async
    gap analysis, and cross-release change comparison.