{"uid":"cap_bHeYHgOParlCuN1yVDSMP","slug":"agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-42e41439","name":"Semantic HTML Pruner 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://agentdiet.dev/v1/semantic-html-pruner)","url":"https://agentdiet.dev/v1/semantic-html-pruner?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_JtLSZGj-5dQze-hcoQE9n","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into clean Markdown using budget mode with the query 'payment intents' and cap it at 2000 tokens so I can feed it to my LLM without blowing my context window.","exampleUseCases":[{"title":"Compress docs page for LLM context","prompt":"Grab the page at https://docs.openai.com/api-reference and distill it down to structured Markdown — I want to pass it to my model but I need it under 3000 tokens, so use budget mode with the query 'embeddings'."},{"title":"Extract tables and metadata from a report","prompt":"I have this raw HTML from a financial report — can you distill it into structured JSON tables and pull out the key metadata? Here's the HTML: <html>...</html>. Use structured mode."},{"title":"Skeleton outline of a long article","prompt":"Pull the article at https://techcrunch.com/2024/05/10/ai-agents-are-here and give me just the skeleton outline — headings, subheadings, and key anchors — so I can quickly scan the structure without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25 excerpt), an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio, estimated LLM cost saved in USD, and an ROI multiplier, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint cannot fetch the page","HTML payload is empty or malformed — distillation yields no meaningful content","mode=budget requested without a 'query' parameter — BM25 ranking cannot proceed","max_tokens set below minimum of 20 — rejected with validation error","Paywalled or JavaScript-rendered pages may return incomplete content","x402 payment not completed — request blocked before processing"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before feeding web content to an LLM, especially when working within strict context window limits. It is ideal for agents that repeatedly fetch web pages and need cost-efficient content extraction. The BM25 budget mode is uniquely useful when you have a specific query and a hard token ceiling, outperforming generic scrapers that return full raw text. Prefer it over general-purpose scrapers when compression ratio and LLM cost savings matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:30.680Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-42e41439"}