{"uid":"cap_1VyyXbpkUchs-r4khyOWS","slug":"json-repair-agentdiet-dev-semantic-html-pruner-web-url-distillation-7a39358a","name":"Semantic HTML Pruner – Web URL Distillation 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://json-repair.agentdiet.dev/v1/semantic-html-pruner)","url":"https://json-repair.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_nhTq2gwek7rECbMzcmvrm","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 a webpage (or accepts raw HTML) and distills it into compact, agent-readable content using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into compact markdown, keeping it under 2000 tokens and focusing on the authentication section.","exampleUseCases":[{"title":"Summarize documentation for LLM context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into tight markdown under 1500 tokens — I need to pass the gist to my model without blowing the context window."},{"title":"Topic-focused extraction from a news article","prompt":"Pull this article at https://techcrunch.com/2024/01/15/ai-agents-explainer and extract only the parts about autonomous agents, using budget mode with a 500-token limit."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.apple.com/iphone into structured JSON tables so I can pull out the product specs and pricing tiers cleanly."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","max_tokens set below 20 — validation error","query param missing when mode=budget — may return unfiltered or error","raw HTML too large — may timeout or exceed processing limits","Paywalled or JavaScript-heavy pages may yield poor extraction quality","Payment not fulfilled (402) — request blocked until x402 payment is made"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to dramatically reduce token usage — especially when you have a strict context budget or want BM25-focused relevance filtering. Prefer it over raw scraping when you need clean Markdown, structured tables, or a skeleton outline rather than raw HTML. Ideal for agentic pipelines that read many URLs and need to stay within token cost budgets.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:27.117Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-semantic-html-pruner-web-url-distillation-7a39358a"}