{"uid":"cap_GvZ3TnRMqwByP8uuO_MYZ","slug":"onchain-risk-agentdiet-dev-webpage-distiller-with-bm25-budget-control-543139d8","name":"Webpage Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://onchain-risk.agentdiet.dev/v1/webpage-distiller)","url":"https://onchain-risk.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_FIrX1mIZnnqSacJGG1s4w","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a URL or raw HTML into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, and keep it under 800 tokens using BM25 budget mode focused on 'payment intents'.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into markdown using budget mode with the query 'function calling' and a max of 600 tokens so it fits in my context window."},{"title":"Extract structured product data from e-commerce page","prompt":"Distill https://www.apple.com/iphone into structured mode so I get tables and metadata about the products without all the extra HTML noise."},{"title":"Summarize research paper landing page","prompt":"Take the HTML I'm pasting here and distill it into a skeleton outline so I can quickly see the document structure and main headings without reading the whole thing."}],"resultDescription":"Returns a distilled version of the webpage in the requested mode (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), along with an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may cause incomplete distillation","mode=budget without a query or max_tokens may fall back to default behavior","Payment failure via x402 returns HTTP 402 before processing","Rate limits or upstream fetch timeouts cause delayed or failed responses"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to process web content but must stay within a token budget or reduce LLM costs. It is especially useful when you need BM25-focused extraction to surface only the most query-relevant sections of a page, or when you want structured tables and metadata rather than raw HTML. Prefer it over generic scrapers when you need built-in compression ROI metrics and multiple distillation modes in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:44:48.173Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-webpage-distiller-with-bm25-budget-control-543139d8"}