openapi: 3.2.0
info:
  title: AI Crawler Index Ip Ranges API
  version: '2026-09-01'
  summary: Every AI crawler on the web, what it is for, what blocking it costs you, and the IP ranges its operator publishes — as JSON, CSV, robots.txt and regex.
  description: 'A read-only, static, keyless index of 56 web crawlers operated by 30 companies and projects: what each one is for, the exact robots.txt token and user-agent substring, whether the operator says it obeys robots.txt, how to verify it is genuine, and — the part nobody else publishes — what you lose by blocking it.'
  license:
    name: CC0-1.0
    url: https://creativecommons.org/publicdomain/zero/1.0/
  contact:
    url: https://www.pathwren.workers.dev/about.html
servers:
- url: https://www.pathwren.workers.dev
tags:
- name: IP Ranges
  description: Operator-published prefixes, normalised.
paths:
  /data/ip-sources.json:
    get:
      summary: Which operators publish verifiable IP ranges, and where
      operationId: listIpSources
      tags:
      - IP Ranges
      responses:
        '200':
          description: Source list
          content:
            application/json: {}
  /ip-ranges/all.json:
    get:
      summary: Union of every operator-published prefix, grouped by source
      operationId: getAllIpRanges
      tags:
      - IP Ranges
      responses:
        '200':
          description: 1887 IPv4 and 1056 IPv6 prefixes
          content:
            application/json: {}
  /ip-ranges/all.txt:
    get:
      summary: The same prefixes, one CIDR per line
      tags:
      - IP Ranges
      operationId: getAllIpRangesText
      responses:
        '200':
          description: 'Plain text, # comments'
          content:
            text/plain:
              schema:
                type: string
  /ip-ranges/{source}.json:
    get:
      summary: One operator's published prefix list, normalised
      operationId: getIpRangeSource
      tags:
      - IP Ranges
      parameters:
      - name: source
        in: path
        required: true
        description: Source slug, from /data/ip-sources.json
        schema:
          type: string
          enum:
          - openai-gptbot
          - openai-searchbot
          - openai-chatgpt-user
          - google-googlebot
          - google-special
          - google-user-triggered
          - google-user-triggered-google
          - bing-bingbot
          - apple-applebot
          - duckduckgo-duckduckbot
          - perplexity-bot
          - perplexity-user
      responses:
        '200':
          description: Prefixes with provenance
          content:
            application/json: {}
        '404':
          description: No such source