{"uid":"cap_tfH09m4t379IbpAClkPps","slug":"clanker-banker-llm-pack-web-fetcher-b4c2d6c1","name":"clanker-banker LLM-Pack Web Fetcher","description":"Clanker Banker llm-pack: URL→token-budgeted LLM-ready markdown for AI agents. html-to-markdown, web scrape offload, RAG ingest pack. ~$0.005 USDC Base x402. Pay-to-probe on /v1/inspect|/v1/resolve. Quote: GET /v1/quote?tool=llm-pack.","url":"https://clanker-banker.agentfetcher.workers.dev/v1/llm-pack","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Public URL to convert into token-budgeted LLM-ready markdown for model context / RAG"},"noCache":{"type":"boolean","description":"Skip cache and re-fetch the page"},"maxTokens":{"type":"number","description":"Token budget for packed markdown (500–32000, default 4000)"}}},"responseSchema":{"type":"json","example":{"title":"Example Domain","usage":"Paste markdown into your model context.","markdown":"# Example Domain\n\nSource: https://example.com\n\n...","truncated":false,"approxTokens":120}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.00375/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.00375","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.00375","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Dr-xiIdQPcChxrat6XjAZ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.00375","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public URL and converts its content into token-budgeted, LLM-ready markdown suitable for model context windows or RAG pipelines","exampleAgentPrompt":"Fetch the content of https://example.com/article and pack it into LLM-ready markdown with a 6000 token budget so I can use it in my RAG pipeline.","exampleUseCases":[{"title":"RAG pipeline web content ingestion","prompt":"Grab the content from https://docs.openai.com/api-reference and convert it into clean markdown capped at 8000 tokens so I can feed it into my retrieval system."},{"title":"Agent context enrichment from live URL","prompt":"My agent needs to reason about this page — fetch https://blog.anthropic.com/claude-research and pack it into LLM-ready markdown, keep it under 4000 tokens."},{"title":"Fresh page fetch bypassing cache","prompt":"Get a fresh copy of https://news.ycombinator.com/news — skip the cache and pack it into LLM-ready markdown with a 3000 token limit."}],"resultDescription":"Returns token-budgeted LLM-ready markdown text derived from the fetched public URL, truncated or summarized to fit within the requested token limit (default 4000, range 500–32000). Content is cleaned and formatted for direct use in model context windows or RAG retrieval pipelines.","failureModes":["402 Payment Required — returned when no valid x402 payment header is provided; must pay $0.00375 USDC per call","Invalid or unreachable URL — if the target URL is not publicly accessible, the fetch will fail","Token budget out of range — maxTokens outside 500–32000 will be rejected or clamped","Timeout — very large or slow pages may exceed worker processing limits","Non-HTML content — binary files or media URLs may not convert meaningfully to markdown"],"whenToPreferThis":"Use this endpoint when you need to fetch a public URL and immediately prepare its content for LLM ingestion within a controlled token budget — especially for RAG pipelines, agent context enrichment, or single-page content extraction. Prefer this over raw HTTP fetching when you need clean, token-aware markdown output without building your own scraping and chunking pipeline. The x402 micropayment model makes it suitable for pay-per-use agent workflows without subscription overhead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-16T00:36:06.954Z","isFirstParty":false}