{"uid":"cap__MftcB7iEPAYkg8RXu1Lx","slug":"onchain-risk-agentdiet-dev-semantic-html-pruner-web-url-to-agent-72a880be","name":"Semantic HTML Pruner – Web URL to Agent-Ready Tokens","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/semantic-html-pruner)","url":"https://onchain-risk.agentdiet.dev/v1/semantic-html-pruner?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_cIwsKTKP4wQ8DyOl-x2zz","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 accepts raw HTML) and distills it into compact, token-efficient content using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode focused on 'payment intents', keeping it under 1000 tokens.","exampleUseCases":[{"title":"Compress docs for LLM pipeline","prompt":"Grab https://docs.openai.com/api-reference and distill it into clean markdown in budget mode with a focus query on 'embeddings', capped at 800 tokens — I need to feed it to my agent without blowing my context window."},{"title":"Extract structured product data from storefront","prompt":"Take this URL https://example-shop.com/products and run it through structured mode so I get back the product tables and metadata in JSON format, without all the nav and footer noise."},{"title":"Outline a long article for quick review","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) into a skeleton outline so I can see the section headings and key structure without reading the whole page."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt depending on mode), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Also includes cache hit/miss status and billing info.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked origins","Token budget too small (below 20) returns validation error","Mode enum mismatch returns 400-style error","Payment not attached or x402 payment fails results in 402 response","Raw HTML payload too large may be rejected","BM25 query with no relevant matches returns minimal content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content within a strict token budget, or when raw HTML is too noisy or large to pass directly to an LLM. It is especially valuable when you need BM25-ranked relevance filtering around a specific query, or when you want structured extraction (tables, metadata) or a skeleton outline rather than full page content. Prefer it over generic scraping tools when token efficiency and LLM cost reduction are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:17.516Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-semantic-html-pruner-web-url-to-agent-72a880be"}