{"uid":"cap_t-uvEZU2EAh3xN71wk86E","slug":"domain-osint-agentdiet-dev-web-content-distiller-with-bm25-budget-aec40a2c","name":"Web Content 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://domain-osint.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://domain-osint.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_4HvA9SC7brw-EHvza8s1r","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, keeping only the most relevant parts about payment intents — use budget mode with a max of 2000 tokens and focus the BM25 query on 'payment intents'.","exampleUseCases":[{"title":"LLM context window cost reduction","prompt":"Fetch https://docs.openai.com/api-reference and distill it down to under 1500 tokens using budget mode, focused on 'function calling', so I can include it in my agent prompt without blowing up my token costs."},{"title":"Structured data extraction from webpage","prompt":"Pull the page at https://example.com/pricing and distill it in structured mode so I get the pricing tables and metadata as clean JSON rather than a wall of HTML."},{"title":"Skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline — just the section headers and key structure — so I can quickly navigate what's there without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may cause partial distillation","max_tokens below minimum (20) rejected with validation error","BM25 query in budget mode with no relevant content may return minimal excerpt","Rate limiting or payment failure (HTTP 402) if payment not properly attached","Timeout on slow-loading URLs may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to shrink a webpage or HTML blob to fit an LLM context window, especially when you want BM25-ranked relevance filtering against a specific query topic. It's ideal over generic scrapers when you need token-budget guarantees, ROI metrics on compression, or multiple distillation modes (markdown, structured, skeleton). Prefer it when cost savings on downstream LLM calls matter and you want proof of compression efficiency.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:00.417Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-content-distiller-with-bm25-budget-d595fba0"}