{"uid":"cap__3Mk80l8RboKMaouWNtdr","slug":"serp-extract-agentdiet-dev-web-url-html-bm25-budget-controlled-b9e81c4d","name":"Web URL & HTML BM25 Budget-Controlled Distillation","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/pdf-extract)","url":"https://serp-extract.agentdiet.dev/v1/pdf-extract?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_KEQPiTezha-9P2EvxQyRv","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 payload into compact agent-ready tokens using BM25-ranked budget control to minimize token consumption","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown using budget mode, focusing on 'payment intents', and cap the output at 500 tokens so I don't blow my LLM context.","exampleUseCases":[{"title":"Budget-capped research article distillation","prompt":"Grab the article at https://arxiv.org/abs/2401.00001 and distill it in budget mode focused on 'transformer attention mechanisms', keeping the output under 300 tokens so it fits in my prompt."},{"title":"Structured table extraction from HTML","prompt":"I have some raw HTML from a financial data page — can you distill it into structured JSON tables so I can pull out the numbers without parsing the whole mess myself?"},{"title":"Skeleton outline of documentation page","prompt":"Get the skeleton outline of https://docs.openai.com/api-reference so I can see the high-level structure of their docs without reading the full content."}],"resultDescription":"Returns a `data` object containing distilled content in the requested format (markdown, structured JSON, skeleton outline, or BM25 budget excerpt), plus an `roi_proof` object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","HTML too malformed to parse results in empty or partial distillation","max_tokens set below minimum (20) triggers validation error","BM25 query missing when mode=budget may return unfiltered or empty excerpt","Payment not attached (HTTP 402) blocks execution","Rate limit or upstream timeout on slow pages may cause latency spikes"],"whenToPreferThis":"Choose this endpoint when you need to distill a specific URL or raw HTML into token-efficient content and want precise BM25-ranked budget control over output size. It is especially valuable when you need to stay within a strict token ceiling before passing content to an LLM, reducing costs. Prefer it over generic scrapers when compression ratio and ROI proof (tokens saved) matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:17.550Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-html-bm25-budget-controlled-b9e81c4d"}