{"uid":"cap_EFQLdMQfODaSx3NUnbLwD","slug":"onchain-risk-agentdiet-dev-url-html-distillation-with-bm25-budget-ca41b573","name":"URL & HTML Distillation 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/prompt-compress)","url":"https://onchain-risk.agentdiet.dev/v1/prompt-compress?utm_source=zero.xyz","method":"POST","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_xIA-G4d3cWifTbQs29-Vq","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 payload into compact agent-ready tokens using BM25-ranked budget control and multiple distillation modes.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown for my agent, using budget mode focused on 'payment intents' and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-budget extraction for LLM context","prompt":"Fetch https://docs.openai.com/api-reference and compress it into at most 800 tokens using budget mode, focused on 'rate limits', so I can fit it into my prompt without blowing my context window."},{"title":"Structured data extraction from HTML","prompt":"I've got some raw HTML from a product listing page — can you distill it into structured JSON tables and metadata so I can parse out the product names and prices easily?"},{"title":"Skeleton outline of a long article","prompt":"Pull down https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page so I can quickly understand its structure and main sections."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton outline, or BM25 budget 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 ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint cannot fetch or distill the page","Raw HTML is malformed or empty — distillation produces empty or error result","max_tokens set below minimum (20) — validation error returned","BM25 query missing when mode=budget — may produce unguided compression","Token budget too small to capture meaningful content — truncated or low-quality output","Payment failure via x402 — request blocked before processing"],"whenToPreferThis":"Choose this endpoint when you need to fit web content into a strict LLM token budget and want BM25-ranked relevance scoring to prioritize the most query-relevant passages. It is especially valuable when you have a specific focus query (mode=budget) and need provable token savings with ROI metrics. Prefer it over generic web scrapers when you need multiple output formats (markdown, structured, skeleton) and built-in compression reporting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:53.880Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-url-html-distillation-with-bm25-budget-ca41b573"}