{"uid":"cap_BHWIxp4_B7y59HctoVB72","slug":"hn-pulse-agentdiet-dev-web-url-context-distiller-bm25-budget-control-dcd11a8a","name":"Web URL 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://hn-pulse.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://hn-pulse.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_oL4sgokHOQDrd4QTyqtu4","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and compresses it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget extraction modes.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown, keeping it under 800 tokens and focusing on the query 'payment intents API' using budget mode.","exampleUseCases":[{"title":"Compress docs page for LLM ingestion","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured JSON tables so I can pass just the key info to my model without blowing my context window."},{"title":"BM25-focused extraction for research","prompt":"I need to pull only the parts of https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) that are relevant to 'attention mechanism' — use budget mode with a 500 token ceiling."},{"title":"Skeleton outline of a long article","prompt":"Give me a skeleton outline of https://www.wired.com/story/ai-agents-future-work so I can quickly scan its structure without reading the whole thing."}],"resultDescription":"Returns a distilled payload containing the compressed content (markdown, structured tables, skeleton, 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 a cache status indicator showing whether the result was freshly fetched or served from cache.","failureModes":["Invalid or unreachable URL returns an error status","HTML too short or empty produces minimal distillation output","mode=budget without a query or max_tokens may fall back to default behavior","Token ceiling too low (below 20) is rejected by schema validation","Rate limiting or payment failure (HTTP 402) blocks the request","Paywalled or bot-blocked pages may return incomplete or empty content"],"whenToPreferThis":"Choose this endpoint when an agent needs to ingest web content but must stay within a token budget or minimize LLM inference costs. It is especially useful over raw HTML fetching when the page is large, boilerplate-heavy, or only partially relevant to a query. The BM25 budget mode makes it distinctly better than generic scraping when you need topically focused extraction with a hard token ceiling. Prefer this over generic web scrapers when ROI tracking and compression metrics are needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T07:52:38.890Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-context-distiller-bm25-budget-control-3d532bfb"}