{"uid":"cap_N9YxFLWk3Tvm5R20XaCYj","slug":"llms-generator-agentdiet-dev-agentdiet-paywall-clean-web-distiller-8dccec55","name":"AgentDiet Paywall-Clean Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://llms-generator.agentdiet.dev/v1/paywall-clean-extract)","url":"https://llms-generator.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","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":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_cUd6xKcQPOPNrv6h6aVT8","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, keeping it under 800 tokens and focusing on 'payment intent setup'.","exampleUseCases":[{"title":"Research article summarization for agent","prompt":"Grab the article at https://techcrunch.com/2025/05/01/openai-news and distill it into compact markdown so I can read just the key points without all the ads and navigation junk."},{"title":"Budget-capped relevant excerpt extraction","prompt":"Pull the content from https://docs.anthropic.com/claude/reference and extract only the parts relevant to 'rate limits', keeping the output under 500 tokens."},{"title":"Structured data extraction from web page","prompt":"Fetch https://finance.yahoo.com/quote/AAPL and give me a structured JSON summary of the page — things like price tables, metadata, and key stats."}],"resultDescription":"Returns a JSON object with a 'data' field containing distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache hit/miss status and billing info.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return incomplete or empty content","max_tokens too low may result in heavily truncated output losing key context","query field required but missing when mode=budget","HTML payload too large may be rejected or truncated","Network timeouts on slow-loading pages"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and reason over web page content but wants to minimize LLM token consumption. It is especially useful when pages have heavy boilerplate, ads, or navigation clutter. The BM25 budget mode makes it uniquely suited for focus-extracting only the most relevant passages given a specific query within a hard token ceiling — something generic scrapers don't offer. Prefer this over raw fetch tools when token cost and context window size are constraints.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:02.909Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-agentdiet-paywall-clean-web-distiller-8dccec55"}