{"uid":"cap_iO1xRZvjmmfR1NvT8WAB-","slug":"onchain-risk-agentdiet-dev-web-url-html-distiller-with-bm25-budget-9fc804a5","name":"Web URL & HTML Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://onchain-risk.agentdiet.dev/v1/paywall-clean-extract)","url":"https://onchain-risk.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"POST","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_8dBRiO3Pe7ehP0MFqbKw6","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact, agent-ready tokens using BM25-ranked budget trimming with configurable output modes","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/api and distill it in budget mode with the query 'payment intents' and a max of 500 tokens, so I only get the most relevant content.","exampleUseCases":[{"title":"Fit documentation into LLM context window","prompt":"Pull the Stripe docs from https://stripe.com/docs/api/charges and distill them using budget mode focused on 'refunds', keeping it under 300 tokens — I want only what's relevant to my question without blowing my context window."},{"title":"Extract structured tables from a financial page","prompt":"Take this HTML I'm pasting in and distill it in structured mode so I get clean JSON tables and metadata — I need the pricing tiers from this SaaS vendor's pricing page without all the surrounding noise."},{"title":"Skeleton outline of a long article","prompt":"Grab the article at https://techcrunch.com/2024/05/01/ai-agents-future and give me a skeleton outline so I can see the headings and structure before deciding whether to read the full thing."}],"resultDescription":"Returns a distilled version of the webpage or HTML in the requested mode (markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt), along with an ROI proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","Invalid or missing URL with no HTML fallback — required field validation error","Token budget too small (below 20) — minimum validation failure","BM25 query missing when mode=budget — may return unfiltered or error response","Rate limiting or payment failure via x402 — 402 response requiring payment","Malformed HTML input — may produce poor distillation quality"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web pages or HTML documents before feeding content to an LLM, especially when you have a specific topic query (BM25 mode) or a hard token budget ceiling. It is particularly valuable over raw fetch-and-paste approaches when context windows are limited or LLM API costs are a concern. The BM25 budget mode is uniquely suited for targeted content retrieval from long documents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:37.749Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-html-distiller-with-bm25-budget-782a3d07"}