{"uid":"cap_naNVI0KTVNU2kYmwaNtZ6","slug":"whale-momentum-agentdiet-dev-dom-stripper-web-distillation-with-bm25-e54f0729","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://whale-momentum.agentdiet.dev/v1/dom-stripper)","url":"https://whale-momentum.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_6LfiGz-9OVCmXqNF15gqj","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"whale-momentum.agentdiet.dev","brandSlug":"whale-momentum-agentdiet-dev-mpp","brandBaseUrl":"https://whale-momentum.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean Markdown, keeping it under 2000 tokens and focusing on the BM25 query 'payment intents setup'?","exampleUseCases":[{"title":"LLM context window compression","prompt":"Pull the content from https://docs.anthropic.com/claude/reference and compress it into budget mode with a 1500 token ceiling, focused on the query 'tool use function calling' — I need to fit it into my prompt without blowing the context limit."},{"title":"Structured table extraction from e-commerce page","prompt":"Distill https://aws.amazon.com/ec2/pricing/ in structured mode so I get the pricing tables as clean JSON — I want to compare instance types without scraping the whole HTML mess."},{"title":"Quick Markdown summary of a news article","prompt":"Strip down this HTML I'm pasting — it's the raw source of a TechCrunch article — into readable Markdown mode so I can read the actual story without all the ads and nav clutter."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with an roi_proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint returns an error status","URL points to a non-HTML resource (PDF, binary) — distillation may fail or return empty data","max_tokens set too low (below 20) — rejected by schema validation","mode=budget used without providing a query — BM25 scoring has no focus signal","Raw HTML provided is malformed or empty — distillation returns minimal or empty output","Network timeout fetching the target URL — returns error status","Payment not included or insufficient — HTTP 402 response blocking execution"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working within strict context window budgets. It is ideal for agent pipelines that need to read documentation, news, or product pages without incurring high LLM token costs. Prefer the budget+BM25 mode when you have a specific question and want only the most relevant passage from a page. Use structured mode when the page contains tables or metadata you want as JSON. Prefer this over raw HTTP fetch + manual parsing when you want compression ROI metrics included automatically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:10.356Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-dom-stripper-web-distillation-with-bm25-e54f0729"}