{"uid":"cap_zy9lnJ8Ft1PBn0F7DHXkL","slug":"domain-osint-agentdiet-dev-web-url-distillation-compact-token-42167bb1","name":"Web URL Distillation & Compact Token Extraction API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://domain-osint.agentdiet.dev/v1/pdf-extract)","url":"https://domain-osint.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_Q8eZ5Lh0d2GBY6d2Z6qhE","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage (or accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Can you distill the content at https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intents workflow'?","exampleUseCases":[{"title":"Documentation page for agent context","prompt":"Fetch and distill https://docs.openai.com/api-reference into markdown so I can feed it to my agent without burning through my context window — use budget mode with a 1500 token ceiling and focus on 'function calling'."},{"title":"Competitor research via structured extraction","prompt":"Pull the pricing page at https://anthropic.com/pricing and extract it in structured mode so I get a clean JSON table of their plans and costs."},{"title":"Skeleton outline of a long article","prompt":"Give me a skeleton outline of this URL https://en.wikipedia.org/wiki/Large_language_model — just the headings and key structural elements, as compact as possible."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt depending on mode), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 response — distillation fails with error status","URL points to non-HTML content (e.g. binary file) — may return empty or garbled output","max_tokens ceiling too low (below 20) — rejected by schema validation","BM25 query returns no matching segments — budget excerpt may be minimal","Rate limiting or payment failure via x402 — request blocked","Very large pages may time out before full fetch completes"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read or process webpage content but must stay within a token budget — especially useful when feeding documentation, research pages, or competitor sites into an LLM context window. Prefer it over generic scrapers when you need built-in compression metrics (tokens saved, ROI multiplier) and multiple distillation modes (markdown, structured, skeleton, budget). The BM25 budget mode is uniquely suited when you have a specific query focus and a hard token ceiling.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:46.733Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-distillation-compact-token-42167bb1"}