{"uid":"cap_P0Y-ckn-vtuHupBwXun1V","slug":"serp-extract-agentdiet-dev-web-url-distillation-content-extraction-api-fa800507","name":"Web URL Distillation & Content Extraction 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/paywall-clean-extract)","url":"https://serp-extract.agentdiet.dev/v1/paywall-clean-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_UFGhzTy2-bBOddo9FsOz-","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 BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown, then give me a budget excerpt focused on 'webhook events' under 500 tokens so I can pass it to my LLM without blowing the context window.","exampleUseCases":[{"title":"LLM context window cost reduction","prompt":"Grab the content from https://openai.com/blog/gpt-4o and distill it into markdown mode so I can feed it to my agent without wasting tokens — show me how much I saved."},{"title":"Focused research on specific topic","prompt":"Fetch https://docs.aws.amazon.com/lambda/latest/dg/welcome.html in budget mode with the query 'cold start latency' and cap it at 300 tokens so I only get the most relevant section."},{"title":"Structured data extraction from webpage","prompt":"Pull the page at https://en.wikipedia.org/wiki/Large_language_model and give me the content in structured mode so I get the tables and metadata as clean JSON rather than raw HTML."}],"resultDescription":"Returns a distilled version of the requested webpage in the chosen format (Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt), along with an roi_proof object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","URL behind a hard paywall that cannot be fetched returns empty or partial content","Exceeding the x402 payment budget or missing payment headers results in 402 Payment Required","mode=budget without a query parameter may return unfiltered or degraded output","Very large pages may exceed processing limits or produce high token counts before compression","HTML parameter conflicts with URL fetch if both are provided simultaneously"],"whenToPreferThis":"Choose this endpoint when your agent needs to ingest web content but must stay within LLM context or cost limits — especially when you need BM25-ranked focused excerpts (mode=budget), clean Markdown distillation, or structured JSON extraction from arbitrary URLs. Prefer it over generic scrapers when token economy and ROI tracking matter, or when you need to pass web content downstream to an LLM and want compression metrics to justify the fetch cost.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:55.849Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-distillation-content-extraction-api-fa800507"}