{"uid":"cap_FU-38nHEfYQtH4iz5gdIW","slug":"domain-osint-agentdiet-dev-webpage-distiller-compact-agent-ready-ed0de22c","name":"Webpage Distiller — Compact Agent-Ready Token Extraction","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/webpage-distiller)","url":"https://domain-osint.agentdiet.dev/v1/webpage-distiller?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_oUYM4UxahWfenZeVLGhk_","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 URL or accepts raw HTML and distills it into compact, agent-consumable content using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into markdown mode and keep it under 800 tokens, focused on the query 'payment intents API'.","exampleUseCases":[{"title":"Research summary within context window","prompt":"Grab the article at https://arxiv.org/abs/2401.00001 and distill it into markdown, capping it at 500 tokens so I can pass it to my model without blowing the context window."},{"title":"Structured data extraction from landing page","prompt":"Fetch https://example-saas.com/pricing and extract it in structured mode so I get the pricing tiers and features as clean JSON tables."},{"title":"BM25-focused competitor research snippet","prompt":"Pull https://competitor.com/about and give me only the parts relevant to 'fundraising and investors' using budget mode, max 300 tokens."}],"resultDescription":"Returns a 'data' object containing distilled content in the requested mode (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an roi_proof block showing raw vs. distilled token counts, compression ratio, tokens saved, estimated LLM cost saved in USD, and a billing record. Optional cache status and latency are also included.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","Raw HTML too large or malformed — distillation may be incomplete or fail","max_tokens set below minimum of 20 — request rejected with validation error","mode=budget used without providing a query — BM25 ranking has no focus, may return degraded results","Payment not attached or insufficient — HTTP 402 returned before processing begins","Requested URL is behind authentication or a CAPTCHA — fetch fails silently or returns empty content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget or minimize LLM inference costs. It is especially valuable when passing webpage content to a downstream LLM call, since it returns compression ratio and cost-saved metrics alongside the distilled content. Prefer it over raw HTTP fetches when you need clean Markdown, structured table extraction, or BM25-ranked relevance filtering of a specific page. It is not designed for full-site crawls or sitemap traversal.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:27.889Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-webpage-distiller-compact-agent-ready-ed0de22c"}