{"uid":"cap_hhttQYAoUu6xxu_5D5lXy","slug":"serp-extract-agentdiet-dev-web-url-distiller-with-bm25-budget-control-19e22d7c","name":"Web URL 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/pdf-extract)","url":"https://serp-extract.agentdiet.dev/v1/pdf-extract?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__2jU8i5UXSeGdK4PyjHS1","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 processes raw HTML) and compresses it into compact, agent-ready tokens using configurable distillation modes including markdown, structured, skeleton, or BM25-focused budget excerpts.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 1000 tokens using budget mode with a focus query of 'payment intents'?","exampleUseCases":[{"title":"Cheap LLM web grounding for agent pipelines","prompt":"Fetch https://openai.com/pricing and distill it into structured mode so I get clean tables and metadata without wasting tokens on nav bars and footers."},{"title":"Budget-capped competitor research snippet","prompt":"Pull https://www.anthropic.com/claude and give me only the most relevant 500 tokens about pricing using budget mode with the query 'model pricing tiers'."},{"title":"Skeleton outline of a long documentation page","prompt":"Distill https://docs.aws.amazon.com/s3/latest/userguide/Welcome.html into skeleton mode so I can see the high-level structure before deciding what sections to read in full."}],"resultDescription":"Returns a distilled data object containing the page content in the chosen format (markdown, structured tables/metadata, skeleton outline, or BM25-focused excerpt), plus ROI proof metrics (raw token count, distilled token count, tokens saved, compression ratio, LLM cost saved in USD, ROI multiplier), billing details, and cache status.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","HTML payload is malformed and cannot be parsed cleanly","mode=budget used without a query parameter — BM25 scoring may be undefined","max_tokens ceiling set too low (below 20) — request rejected by schema validation","Target URL requires JavaScript rendering which the fetcher does not support","Rate limiting or payment failure via x402 causes the request to be rejected"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost. It is especially valuable when working with long documentation pages, competitor sites, or any URL where raw content would exceed context limits. The BM25 budget mode makes it uniquely useful when you have a specific query focus and a hard token ceiling. Prefer it over raw HTML fetching or generic scrapers when compression ratio and cost savings are first-class concerns.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:46.304Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-distiller-with-bm25-budget-control-19e22d7c"}