{"uid":"cap_ebp9J4FQjGbe3EvpXdeqX","slug":"token-intel-agentdiet-dev-dom-stripper-web-distillation-with-bm25-35a2de69","name":"DOM Stripper — Web 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://token-intel.agentdiet.dev/v1/dom-stripper)","url":"https://token-intel.agentdiet.dev/v1/dom-stripper?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_DAV1qzWCKl3RwDAlhRVjG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budgeted excerpt","exampleAgentPrompt":"Strip this page down to clean Markdown for me — https://stripe.com/docs/api — and keep it under 2000 tokens focused on the authentication section.","exampleUseCases":[{"title":"LLM context window cost trimming","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with the query 'rate limits' capped at 500 tokens — I need to fit it into my prompt without blowing my context window."},{"title":"Structured data extraction from product page","prompt":"Pull the product specs table from https://www.apple.com/macbook-pro/specs/ and return it as structured JSON so I can compare it against other laptops."},{"title":"Research summary from news article","prompt":"Distill this article URL https://techcrunch.com/2025/05/01/openai-raises-40b into readable Markdown, cutting out all the ads and navigation junk — I just want the core story text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables, skeleton outline, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache metadata (HIT/MISS, latency) and billing details.","failureModes":["URL is unreachable or returns non-200 — likely returns an error status","HTML payload is empty or malformed — distillation may return minimal or empty content","Token budget too low (below 20) — rejected by schema validation","BM25 query missing when mode=budget — may fall back to default or return error","Rate limiting or payment failure via x402 — 402 response if payment not satisfied","Timeout fetching large or slow pages — may return partial content or timeout error"],"whenToPreferThis":"Choose this endpoint when you need to preprocess web content before sending it to an LLM, especially when token cost or context window size is a concern. It is uniquely suited for agent pipelines that need to fetch and compress arbitrary URLs on the fly, with BM25-based relevance filtering to focus on a specific query topic. Prefer it over raw fetch+parse when you want measurable token savings with ROI metrics, or when you need multiple output formats (Markdown, structured JSON, skeleton, budget excerpt) from the same source.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:16.652Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-dom-stripper-web-distillation-with-bm25-35a2de69"}