{"uid":"cap_KoxhG7SMWDo_3yBNFrwcK","slug":"defi-yield-agentdiet-dev-web-url-distillation-into-compact-agent-34a6518c","name":"Web URL Distillation into Compact Agent-Ready Tokens","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/pdf-extract)","url":"https://defi-yield.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 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_al0OJm86SuOADRzW_0p8H","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 and distills a webpage URL or raw HTML into compressed, token-efficient Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt for AI agent consumption.","exampleAgentPrompt":"Fetch https://stripe.com/docs/api/charges and distill it into compact markdown with a strict budget of 2000 tokens, focusing on 'charge creation parameters'.","exampleUseCases":[{"title":"Token-efficient docs ingestion for agents","prompt":"Grab https://docs.openai.com/api-reference and distill it into structured tables — I want metadata and key fields without burning through my token budget."},{"title":"BM25-focused web research with token cap","prompt":"Distill https://en.wikipedia.org/wiki/Ethereum in budget mode with the query 'proof of stake consensus' and cap it at 1500 tokens so I only get the relevant parts."},{"title":"Skeleton outline for rapid page navigation","prompt":"Pull https://www.sec.gov/cgi-bin/browse-edgar and give me a skeleton outline of the page structure so I can see what sections exist without reading the whole thing."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt) under the 'data' key, alongside ROI metrics (raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD), cache status (HIT/MISS), and billing details including the fee charged.","failureModes":["Invalid or unreachable URL returns a fetch error or non-200 status","Missing required 'url' parameter causes a 400 validation error","mode=budget without a 'query' parameter may return unfiltered or empty content","max_tokens set below 20 triggers schema validation failure","Rate limits or payment failures (x402) result in 402 Payment Required responses","Heavily JavaScript-rendered pages may return incomplete or empty HTML"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read or reference a webpage but must stay within a token budget, minimize LLM costs, or receive content in a structured/outlined format rather than raw HTML. It is especially valuable for processing large documentation pages, financial filings, or reference sites where only a focused subset of content is needed (budget+BM25 mode). Prefer this over general web scraping tools when token efficiency and cost ROI metrics matter to the downstream workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:49.828Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-url-distillation-into-compact-agent-34a6518c"}