{"uid":"cap_SjKnv7SmuFC-Z6gFzQoud","slug":"serp-extract-agentdiet-dev-web-url-distiller-context-bloat-eliminator-63be4948","name":"Web URL Distiller & Context Bloat Eliminator","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://serp-extract.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 distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_27ghA9iHAbdtbv5Jalc6D","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://docs.stripe.com/payments/accept-a-payment into compact markdown and cap it at 800 tokens, focusing the BM25 budget on 'webhook event types'.","exampleUseCases":[{"title":"Fit docs into LLM context window","prompt":"Grab the OpenAI pricing page at https://openai.com/pricing and distill it down to under 600 tokens in budget mode, focused on 'GPT-4o pricing per token' — I need it small enough to fit in my prompt."},{"title":"Extract structured tables from a news article","prompt":"Take https://techcrunch.com/2024/01/15/ai-funding-roundup and distill it in structured mode so I get the funding tables and key metadata as clean JSON, stripping all the editorial fluff."},{"title":"Skeleton outline of lengthy documentation","prompt":"Distill https://docs.aws.amazon.com/lambda/latest/dg/welcome.html in skeleton mode so I get a high-level outline of the page sections without any of the body content — I just need the structure."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked 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. Optionally includes billing details and cache hit/miss status with latency.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","HTML payload too large to process within service limits","BM25 budget mode requires a query string — missing query may fall back to unfiltered mode","max_tokens set below minimum of 20 causes a validation error","Mode enum value not recognized — defaults to markdown","Payment not authorized via x402 — 402 response with payment instructions returned"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a web page but must stay within a token budget or avoid sending bloated HTML to an LLM. It is especially valuable in agentic pipelines where every token costs money, when doing RAG over live web content, or when you need structured or skeleton extraction rather than raw HTML. Prefer it over generic scrapers when you want built-in BM25 relevance filtering, ROI telemetry, and direct compatibility with MCP/A2A agent toolchains.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:17.023Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-distiller-context-bloat-eliminator-63be4948"}