{"uid":"cap_sXf7wS4CfuD3te6BokKO5","slug":"serp-extract-agentdiet-dev-web-url-html-distiller-with-bm25-budget-df5fd435","name":"Web URL HTML Distiller with BM25 Budget Control","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/clean-html)","url":"https://serp-extract.agentdiet.dev/v1/clean-html?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_rRZ7lfvlFPjRFY7YKIYAT","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 URL or raw HTML and distills it into compact, agent-ready tokens using multiple extraction modes including BM25-focused budget trimming","exampleAgentPrompt":"Grab the page at https://stripe.com/docs/payments and distill it into clean markdown with a strict budget of 500 tokens, focusing the BM25 query on 'payment intents'.","exampleUseCases":[{"title":"Distill docs page for agent context","prompt":"Fetch https://docs.openai.com/api-reference and compress it into markdown under 800 tokens so I can inject it into my agent's context window without blowing my budget."},{"title":"Extract structured pricing table from SaaS site","prompt":"Pull the page at https://linear.app/pricing and distill it in structured mode so I get the pricing tiers and feature tables as clean JSON."},{"title":"Focused BM25 snippet from news article","prompt":"Go to https://techcrunch.com/2024/05/01/openai-update/ and extract only the parts most relevant to 'GPT-5 release date' using budget mode with a max of 300 tokens."}],"resultDescription":"Returns a data object containing distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or large pages","Token budget too low (below 20) triggers validation error","Unsupported mode value returns enum validation error","Empty or malformed HTML input causes distillation failure","Payment not provided results in HTTP 402 payment required"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget — especially useful when injecting page content into LLM context windows where cost and length matter. Prefer this over raw fetch/scrape tools when you need BM25-focused relevance trimming, structured extraction, or proven compression ROI metrics. Ideal for agentic pipelines that process many pages and need to minimize LLM token spend.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:11.219Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-html-distiller-with-bm25-budget-df5fd435"}