{"uid":"cap_7KuQNFQyJtQy6r060TRgA","slug":"hn-pulse-agentdiet-dev-context-bloat-eliminator-bm25-budget-web-b6d73bc0","name":"Context Bloat Eliminator — BM25-Budget Web Distiller","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":"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_TQOd0hV3-Vd6RmTu2w-7U","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 and distills a URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budget excerpt, returning compression stats and ROI proof.","exampleAgentPrompt":"Distill https://stripe.com/docs/api into clean Markdown using budget mode, focusing on 'authentication and API keys', and cap the output at 800 tokens — I want to see how many tokens you saved compared to the raw page.","exampleUseCases":[{"title":"Distill docs page into token budget","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with the query 'rate limits and pricing', keeping the output under 600 tokens — show me the compression ratio and how much LLM cost I saved."},{"title":"Clean Markdown from news article","prompt":"Grab https://techcrunch.com/2024/05/01/some-article and strip all the nav, ads, and sidebar noise — just give me clean Markdown of the actual article content."},{"title":"Structured tables from raw HTML","prompt":"I have this raw HTML from a competitor pricing page — distill it in structured mode and pull out all the tables and metadata so I can compare their tiers."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes a cache status (HIT/MISS) and optional billing record.","failureModes":["URL unreachable or returns non-200 — endpoint may error or return empty distillation","HTML payload too large — may exceed processing limits","mode=budget without a query field — BM25 ranking has no focus term","max_tokens set below 20 — rejected by schema validation","Paywalled or JavaScript-rendered pages — raw HTML fetch may return login walls or empty shells","Payment not attached or insufficient — returns HTTP 402 requiring x402 USDC payment"],"whenToPreferThis":"Choose this endpoint when you need to shrink a webpage or HTML blob to fit inside an LLM context window, especially when you want fine-grained token-budget control via BM25 relevance scoring. It is ideal for agentic pipelines that must read external web content cheaply without blowing token budgets. Prefer it over generic scrapers when you need ROI proof (tokens saved, cost saved) or when you want structured output (tables, metadata, skeleton) rather than raw HTML. The budget mode with a query string is particularly powerful for targeted extraction from long documentation or news pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:07.037Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-context-bloat-eliminator-bm25-budget-web-b6d73bc0"}