{"uid":"cap_AArvxHOaskbZuhNIOaByv","slug":"company-enrich-agentdiet-dev-web-distiller-with-bm25-budget-control-90f0bd1b","name":"Web 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://company-enrich.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://company-enrich.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_lcfuRq4RL_PrXevVIIHA7","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compressed Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean Markdown using budget mode focused on the query 'payment intents' with a maximum of 500 tokens, so I can fit it in my prompt without blowing my context window.","exampleUseCases":[{"title":"Token-budget news article extraction","prompt":"Grab https://techcrunch.com/2025/05/01/openai-raises-funding and distill it in budget mode focused on 'funding round valuation' with a max of 300 tokens — I only need the key facts."},{"title":"Structured data pull from a product page","prompt":"Take this raw HTML from an e-commerce product page and distill it into structured JSON tables so I can get the specs, price, and availability without parsing it myself."},{"title":"Docs skeleton for agent orientation","prompt":"Fetch https://docs.anthropic.com/en/api/getting-started and give me a skeleton outline of the page so my agent can quickly navigate its sections without reading everything."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, outline, or BM25 excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Optionally includes billing info and cache hit/miss status with latency.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","HTML payload is empty or malformed — distillation returns minimal or empty data","max_tokens set below 20 — validation error on input schema","BM25 query missing when mode=budget — may fall back to unranked distillation or return error","Payment not provided or insufficient — HTTP 402 response blocking execution","Rate limiting or timeout on target URL — upstream fetch error propagated"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content but must stay within a token budget — particularly useful in agentic pipelines where context window pressure is a concern. The BM25 budget mode makes it uniquely suited for query-focused extraction where only the most relevant passages are needed. Prefer it over generic scrapers when you need built-in compression metrics (ROI proof) and multiple output modes (Markdown, structured, skeleton, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:55.882Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-distiller-with-bm25-budget-control-90f0bd1b"}