{"uid":"cap_neLpGwhzGmRKM-T8xBRAy","slug":"onchain-risk-agentdiet-dev-context-bloat-eliminator-bm25-budget-40c19a3e","name":"Context Bloat Eliminator – BM25 Budget-Controlled Web Distillation","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":"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_EZX53WOkEN0lxggSO1fEw","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 accepts raw HTML and distills it into compact, agent-ready content with BM25-ranked token budget control, returning markdown, structured data, a skeleton outline, or a focused excerpt.","exampleAgentPrompt":"Distill this page https://stripe.com/docs/payments/checkout into budget mode, focusing the BM25 query on 'session creation' and keeping the output under 500 tokens — I need just the relevant bits without blowing my context window.","exampleUseCases":[{"title":"Focused Stripe docs extraction for agent","prompt":"Grab the Stripe docs page at https://stripe.com/docs/api/charges and distill it in budget mode with the query 'capture charge' and a max of 300 tokens — I only want the sections relevant to capturing charges."},{"title":"Compress competitor landing page to markdown","prompt":"Fetch https://openai.com/pricing and convert it to clean markdown — I want the full page distilled so I can compare pricing tiers without all the HTML noise."},{"title":"Skeleton outline of a long article","prompt":"Take this raw HTML I'm pasting and give me a skeleton outline of its structure — just the headings and key sections, nothing else: <html>...</html>"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing metadata.","failureModes":["URL unreachable or returns non-200 response — distillation fails with fetch error","HTML payload too large to process within service limits","max_tokens set below minimum of 20 — rejected with validation error","mode=budget used without a query field — BM25 ranking has no focus signal","Invalid or malformed URL string — schema validation rejects request","Payment failure via x402 — 402 response returned if USDC payment not authorized"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM but want strict token budget control and BM25-ranked relevance filtering rather than naive truncation. It is especially valuable when you have a specific query focus and need only the most relevant sections of a page, or when you want structured JSON tables or a skeleton outline rather than raw markdown. Prefer it over generic scrapers when LLM cost reduction and ROI proof are important, and over the simpler distill endpoint when you need the BM25 budget mode.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:17.712Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-context-bloat-eliminator-bm25-budget-40c19a3e"}