{"uid":"cap_viuHazkfLpXdurvPY2hsN","slug":"ai-crawl-preflight-eda0d69a","name":"AI Crawl Preflight","description":"AI Crawl Preflight ($0.003/call): Preflight a URL before spending a fetch: reads the site's robots.txt (generic and per-AI-crawler verdict, Cloudflare Content-Signal), checks for llms.txt, detects pay-per-crawl (HTTP 402) gating, and whether a markdown variant is served, then returns a plain-language recommendation. Keyless. Pairs with the web reader.","url":"https://x402.botsmith.dev/preflight","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","maxLength":2048,"description":"The URL an agent is considering fetching"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["url","reachable","status","robots","llmsTxt","payPerCrawl","markdownVariant","recommendation"],"properties":{"url":{"type":"string"},"robots":{"type":"object","required":["present","genericAllowed","aiBotsBlocked","contentSignal"],"properties":{"present":{"type":"boolean"},"aiBotsBlocked":{"type":"array","items":{"type":"string"},"description":"Named AI crawlers disallowed for this path"},"contentSignal":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Cloudflare Content-Signal directive, if present"},"genericAllowed":{"anyOf":[{"type":"boolean"},{"type":"null"}],"description":"Is the path allowed for a generic (*) agent"}},"additionalProperties":false},"status":{"anyOf":[{"type":"integer","maximum":9007199254740991,"minimum":-9007199254740991},{"type":"null"}]},"llmsTxt":{"type":"boolean","description":"Site publishes an llms.txt"},"reachable":{"type":"boolean"},"payPerCrawl":{"type":"boolean","description":"URL is gated behind HTTP 402 / pay-per-crawl"},"recommendation":{"type":"string","description":"Plain-language next step for an agent"},"markdownVariant":{"type":"boolean","description":"A markdown/llms variant of the content is available"}},"additionalProperties":false}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_yYh30KRdZjM190DiR3Pm5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Checks a URL's robots.txt, llms.txt, HTTP 402 pay-per-crawl gating, and markdown variant availability before an agent wastes a fetch call, returning a plain-language recommendation.","exampleAgentPrompt":"Before you fetch https://techcrunch.com/2025/01/15/openai-news/, check whether that URL is reachable, whether AI crawlers are allowed, if there's a pay-per-crawl gate or a markdown variant, and tell me whether it's safe to proceed.","exampleUseCases":null,"resultDescription":"A JSON object containing: whether the URL is reachable, the HTTP status code, robots.txt presence and whether generic agents and named AI crawlers (e.g. GPTBot, ClaudeBot) are allowed, a Cloudflare Content-Signal directive if present, a boolean for llms.txt presence, a boolean for HTTP 402 pay-per-crawl gating, a boolean for markdown variant availability, and a plain-language recommendation string advising the agent on next steps.","failureModes":["URL is malformed or exceeds 2048 characters — validation error returned","Target URL is completely unreachable (network timeout, DNS failure) — reachable: false with null status","robots.txt fetch fails — present: false, genericAllowed: null","Service itself is unavailable — HTTP error from preflight endpoint","Payment not attached or insufficient — HTTP 402 from the preflight endpoint itself"],"whenToPreferThis":"Use this before any agent web fetch to avoid wasting credits on blocked, paywalled, or AI-restricted URLs. Ideal when building autonomous crawling pipelines that need to respect robots.txt, detect x402 pay-per-crawl gates, or find markdown-optimized content variants. Pairs with any web reader endpoint to form a preflight-then-fetch pattern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:34:16.562Z","isFirstParty":false}