{"uid":"cap_jJr_DwsA4Kx_VE4D08ISf","slug":"serp-extract-agentdiet-dev-html-url-distiller-with-bm25-budget-control-7dd1871d","name":"HTML/URL Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (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":"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_HATiGKF-adZDicy7fsR2k","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 and distills a URL or raw HTML into compact, token-efficient markdown, structured JSON, skeleton outlines, or BM25-ranked budget excerpts with a strict token ceiling.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it down to 800 tokens max in budget mode, focused on the query 'payment intents API', so I can pass the most relevant content to my LLM without blowing my token budget.","exampleUseCases":[{"title":"Token-budget research for LLM pipelines","prompt":"Pull https://openai.com/pricing and compress it into budget mode with a 500-token ceiling, focused on the query 'GPT-4o pricing per token' — I need just the relevant bits to feed my cost estimator agent."},{"title":"Clean markdown extraction from news article","prompt":"Distill https://techcrunch.com/2024/06/01/some-article into clean markdown mode — strip all the ads and navigation junk and give me just the article content."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML I'm pasting and run it through structured mode to pull out the tables and metadata — I need the product specs in a clean JSON format."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS), billing info, and execution status.","failureModes":["Invalid or unreachable URL returns a fetch error","HTML too large may exceed processing limits","BM25 budget mode with no query defaults to general distillation","max_tokens below 20 rejected by schema validation","Rate limiting or payment failure returns HTTP 402","Malformed raw HTML may produce incomplete distillation output"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working with a fixed token budget or needing to focus on a specific topic within a large page. The BM25 budget mode is uniquely suited for agents that need to extract only the most query-relevant content from a webpage under a strict token ceiling, reducing LLM costs. Prefer it over raw scraping when you need clean markdown or structured output without boilerplate.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:46.245Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-html-url-distiller-with-bm25-budget-control-7dd1871d"}