{"uid":"cap_onh0py0NqhkCb2bNRCtqi","slug":"defi-yield-agentdiet-dev-web-url-distillation-bm25-token-budget-a7b9eb0e","name":"Web URL Distillation & BM25 Token Budget Extractor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://defi-yield.agentdiet.dev/v1/paywall-clean-extract)","url":"https://defi-yield.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 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_SATkClQPr8D7uaUzNOtFZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.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 ROI tracking","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/accept-a-payment into compact markdown, keeping it under 800 tokens and focusing on the setup steps.","exampleUseCases":[{"title":"Reading long docs within context budget","prompt":"Pull the content from https://docs.openai.com/guides/function-calling and compress it into budget mode focused on 'how to define tool schemas', keeping it under 600 tokens so it fits in my prompt."},{"title":"Structured extraction from a product page","prompt":"Fetch https://aws.amazon.com/ec2/pricing/ and give me a structured breakdown of the pricing tables — I want the data as JSON, not a wall of text."},{"title":"Skeleton outline of a research article","prompt":"Grab https://arxiv.org/abs/2307.09288 and give me just the skeleton outline — section headers and key bullet points — so I can decide if it's worth reading in full."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown, structured JSON, skeleton outline, or BM25-ranked excerpt), plus an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","Paywalled or bot-blocked page returns empty or login-wall content","max_tokens too small to include any meaningful content","Invalid mode enum value causes validation error","Raw HTML input too large exceeds processing limits","BM25 query provided without mode=budget — query ignored silently"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a web page but must stay within a token budget, or when the raw HTML of a page is too large and noisy for direct LLM consumption. It is particularly valuable when you need BM25-ranked relevance filtering (mode=budget with a query) to extract only the most pertinent paragraphs, or when you want structured JSON tables from a page. Prefer it over generic scrapers when token cost visibility and compression ROI metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:27.098Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-url-distillation-bm25-token-budget-a7b9eb0e"}