{"uid":"cap_Z6rbNAWNIrCKmPmEvPfWc","slug":"json-repair-agentdiet-dev-dom-stripper-url-html-distillation-with-dbdf1b7b","name":"DOM Stripper: 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://json-repair.agentdiet.dev/v1/dom-stripper)","url":"https://json-repair.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_gNjU2DSDIPotqJ1cNynee","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a webpage URL or raw HTML into compact, agent-ready tokens using configurable extraction modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown — keep it under 1000 tokens and focus on the authentication section using BM25 budget mode?","exampleUseCases":[{"title":"Token-budgeted doc excerpt for RAG pipeline","prompt":"Fetch https://docs.openai.com/api-reference and distill it down to at most 800 tokens focused on 'rate limits', using budget mode with BM25 — I need just the relevant parts for my retrieval pipeline."},{"title":"Summarize competitor landing page","prompt":"Strip https://linear.app down to clean markdown so I can read the key product features without all the nav and footer noise — use markdown mode."},{"title":"Extract structured metadata from raw HTML","prompt":"I have this raw HTML from a product page — can you run it through structured mode to pull out the tables and metadata as JSON so I can compare pricing tiers?"}],"resultDescription":"Returns a JSON object with: a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode); an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional cache status (HIT/MISS with latency); and billing details including fee charged in USD.","failureModes":["URL unreachable or returns non-200 — distillation fails with fetch error","Invalid or malformed URL string — validation error returned","mode=budget used without providing a query — BM25 ranking cannot proceed","max_tokens set below minimum of 20 — schema validation rejection","HTML payload too large — may timeout or exceed processing limits","Paywalled or JavaScript-heavy pages may yield minimal extracted content","Payment (x402) not settled — 402 response before content is returned"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget, or when raw HTML needs to be cleaned and compressed before being passed to an LLM. It is especially valuable when you want BM25-ranked relevance filtering (mode=budget with a query) to extract only the sections pertinent to a specific topic. Prefer it over generic scrapers when you need built-in ROI/compression metrics, multiple output modes (markdown, structured, skeleton), or when cost savings on downstream LLM calls are a priority.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:38.452Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-dom-stripper-url-html-distillation-with-dbdf1b7b"}