{"uid":"cap_WtmFP1Lh82WJ6L4yRlemA","slug":"onchain-risk-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-21911e50","name":"Web URL DOM Distiller (BM25 Budget Mode)","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/dom-stripper)","url":"https://onchain-risk.agentdiet.dev/v1/dom-stripper?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_3-MtWpAVgdtQm0V_gb-nX","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 a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget extraction modes","exampleAgentPrompt":"Pull the content from https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens and focusing the BM25 budget on 'payment intents'.","exampleUseCases":[{"title":"LLM cost-reduction for doc reading","prompt":"Fetch https://docs.openai.com/api-reference and distill it into markdown under 1500 tokens — I want to cut down how many tokens I'm burning when I read API docs."},{"title":"Topic-focused page extraction","prompt":"Grab https://ethereum.org/en/defi/ and extract only the sections most relevant to 'yield farming risks' using budget mode, capped at 800 tokens."},{"title":"Structured data table extraction","prompt":"Distill https://en.wikipedia.org/wiki/List_of_largest_banks into structured JSON tables so I can parse the bank rankings without dealing with all the HTML markup."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), along with ROI proof metrics (raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, llm_cost_saved_usd, roi_multiplier), optional cache metadata (HIT/MISS, latency_ms), and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may produce incomplete distillation","BM25 budget mode with no query falls back to default behavior","max_tokens too low (below 20) rejected by schema validation","Rate limiting or payment failure (HTTP 402) if billing is not set up","Private or bot-protected pages may fail to fetch"],"whenToPreferThis":"Use this endpoint when you need to feed web page content to an LLM but want to minimize token consumption and cost. It is especially valuable when working with long documentation pages, Wikipedia articles, or any URL where raw HTML would be wasteful. Prefer it over raw HTTP fetch + manual parsing when you need built-in BM25 topic focusing, structured JSON extraction, or skeleton outlines. The ROI proof output makes it easy to track token savings across a pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:11.148Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-dom-distiller-bm25-budget-mode-21911e50"}