{"uid":"cap_4c7hv2IiDWwOB2JEBuVwi","slug":"onchain-risk-agentdiet-dev-web-url-distiller-with-bm25-budget-control-b7d4adcc","name":"Web URL 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/clean-html)","url":"https://onchain-risk.agentdiet.dev/v1/clean-html?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_3FgPKWihVBreQh5FMq2-O","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 a webpage or raw HTML and distills it into compact, agent-ready tokens using configurable modes including markdown, structured, skeleton, or BM25-focused budget extraction","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 2000 tokens and focused on the query 'payment intents'?","exampleUseCases":[{"title":"LLM context cost reduction","prompt":"Pull the content from https://docs.openai.com/api-reference and compress it into budget mode focused on 'embeddings endpoint', capped at 1500 tokens — I want to minimize what I send to the model."},{"title":"Structured data extraction from landing page","prompt":"Fetch https://www.acmecorp.com/pricing and distill it in structured mode so I can get the pricing tiers and feature table as clean JSON without all the HTML noise."},{"title":"Quick skeleton outline of documentation","prompt":"Grab https://docs.github.com/en/actions and give me a skeleton outline of the page so I can see the section headers and navigation structure without loading the full content."}],"resultDescription":"Returns a status field, distilled content in the chosen format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or large pages","mode=budget without a query may produce unfocused results","max_tokens set too low may truncate critical content","Paywalled or bot-blocked pages may return incomplete HTML","Missing required 'url' parameter causes validation error"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window and want to minimize token consumption and cost. It is especially valuable when the target page is large, when you have a strict token budget, or when you need BM25-focused extraction to surface only the most query-relevant content. Prefer it over raw fetch tools when compression ratio and LLM cost savings matter, or when you want structured/skeleton output rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:35.440Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-distiller-with-bm25-budget-control-1ba293a4"}