{"uid":"cap_NzxnzweARHq-sG-xK1HDh","slug":"serp-extract-agentdiet-dev-web-url-distillation-bm25-token-budget-api-c7b636c3","name":"Web URL Distillation & BM25 Token Budget API","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/web-scrape)","url":"https://serp-extract.agentdiet.dev/v1/web-scrape?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_r81GIcyylhLSolmJZnhR-","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 web URL (or raw HTML) and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes with token-ceiling control","exampleAgentPrompt":"Grab the page at https://docs.stripe.com/api/charges and distill it into compact markdown — use budget mode with my query 'charge creation parameters' and cap it at 2000 tokens so I'm not blowing my context window.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Fetch https://platform.openai.com/docs/api-reference/chat and distill it into clean markdown — I need it compact enough to fit in my prompt without burning tokens."},{"title":"BM25 excerpt for targeted research","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) in budget mode with my query 'attention mechanism self-attention' and keep it under 1500 tokens — I only want the relevant parts."},{"title":"Structured data extraction from webpage","prompt":"Pull https://news.ycombinator.com and return it in structured mode so I get the post titles, links, and metadata as clean JSON rather than raw HTML soup."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-focused 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) and billing metadata.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","mode=budget used without providing a query — BM25 scoring may fall back to generic compression","max_tokens set too low — may produce truncated or empty excerpts","Raw HTML provided with a URL simultaneously — may cause ambiguity in which source is used","Target page blocks bots or requires authentication — content may be empty or partial","Invalid URL format — schema requires minLength:1 string but malformed URLs will fail fetch"],"whenToPreferThis":"Choose this endpoint when your agent needs to consume web content within a strict token budget, wants BM25-focused excerpts relevant to a specific query, or needs to convert raw HTML into structured JSON or clean markdown before passing it to an LLM. It is ideal over generic scrapers when token cost reduction and compression ratio reporting matter — the roi_proof field lets you audit exactly how many tokens and dollars were saved per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:16.456Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-distillation-bm25-token-budget-api-c7b636c3"}