{"uid":"cap_ZRfRrQP9OFXIOub1n3P7i","slug":"workflows-agentdiet-dev-web-url-context-distiller-bm25-budget-control-4aac1e90","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://workflows.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://workflows.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_WYetdQ8qUqKonO_Xk9z-I","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a web URL or raw HTML into compact, agent-ready tokens using BM25-ranked budget control and multiple distillation modes.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown for me, using budget mode focused on 'payment intents' and capping it at 500 tokens?","exampleUseCases":[{"title":"Compress documentation for LLM context","prompt":"Distill https://docs.openai.com/api-reference into markdown so I can fit the key parts into my context window without blowing the token limit."},{"title":"BM25-ranked budget excerpt for research","prompt":"I need a 300-token excerpt from https://arxiv.org/abs/2310.06825 focused on the query 'transformer attention mechanisms' — use budget mode to pull only the most relevant sections."},{"title":"Skeleton outline of a competitor page","prompt":"Give me a skeleton outline of https://www.anthropic.com/product so I can quickly understand the page structure and main headings without reading the whole thing."}],"resultDescription":"Returns a distilled payload (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved. Also includes cache hit/miss status and billing info.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","URL points to a non-HTML resource (PDF, binary) — distillation may fail or return partial content","max_tokens set too low for meaningful extraction — output may be truncated or empty","BM25 query is too vague — budget excerpt may not surface the most relevant content","Rate limiting or payment failure via x402 — call rejected with 402 or 429","HTML input is malformed — structured or skeleton modes may return incomplete results"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest a web page or HTML document but must stay within a token budget. It is especially useful when you need BM25-ranked relevance filtering (mode=budget) to surface only the content most relevant to a specific query, or when you need a structured/skeleton view of a page rather than raw text. Prefer this over generic scraping when token efficiency and LLM cost savings are the primary concern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:22.060Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-web-url-context-distiller-bm25-budget-control-4aac1e90"}