{"uid":"cap_cwoBXxC31oqe05h9Hl9Ev","slug":"onchain-risk-agentdiet-dev-web-url-html-context-distiller-bm25-budget-0b5b3da9","name":"Web URL & HTML Context Distiller (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/context-bloat-eliminator)","url":"https://onchain-risk.agentdiet.dev/v1/context-bloat-eliminator?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_umCM1CD8CHUUAy3--t-4k","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 URL or raw HTML and distills it into compact, agent-ready tokens using configurable modes including markdown, structured JSON, skeleton outline, or BM25-focused budget excerpts.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into compact markdown, keeping it under 800 tokens and focusing on the 'authentication' topic using budget mode.","exampleUseCases":[{"title":"Compress docs for LLM context window","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured JSON tables so I can fit the key info into my agent's context window without blowing the token limit."},{"title":"BM25 query-focused excerpt extraction","prompt":"I need you to pull https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API and return only the parts relevant to 'error handling' using budget mode with a max of 500 tokens."},{"title":"Quick skeleton outline of a webpage","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model so I can see the page structure and section headers without reading the whole thing."}],"resultDescription":"Returns a status field, distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-scored excerpt depending on mode), an ROI proof object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — fetch failure error","URL resolves to binary/non-HTML content (PDF, image) that cannot be parsed","max_tokens set too low to produce meaningful output — truncation or error","mode=budget used without a query parameter — missing focus query error","Payment not attached or insufficient — HTTP 402 payment required","HTML payload too large — upstream timeout or processing failure"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content within a strict token budget, or when raw web pages produce too much noise and irrelevant content for downstream LLM calls. Particularly valuable when you need BM25-focused excerpts relevant to a specific query, or when you want structured JSON or skeleton outlines rather than raw HTML. Prefer this over generic scrapers when token efficiency and ROI measurement matter — the built-in compression ratio and LLM cost savings reporting make it uniquely suited for cost-conscious agentic pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:43:54.050Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-html-context-distiller-bm25-budget-0b5b3da9"}