{"uid":"cap_f2w5GOSHYEwWgImHFkkk_","slug":"workflows-agentdiet-dev-semantic-html-pruner-web-url-distillation-api-faf9d16f","name":"Semantic HTML Pruner — Web URL Distillation API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/semantic-html-pruner)","url":"https://workflows.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_9dfKEjMNH4tftXT-hQEuH","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a webpage or raw HTML into compact, agent-ready tokens using BM25-ranked budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, use budget mode with the query 'payment intents' and cap it at 2000 tokens so I can include it in my prompt without blowing my context window.","exampleUseCases":[{"title":"Compress docs page for RAG pipeline","prompt":"Fetch and distill https://docs.openai.com/api-reference into structured mode so I can index only the clean content without all the nav and footer noise."},{"title":"BM25-ranked budget excerpt for research","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) in budget mode with the query 'attention mechanism' and a max of 1500 tokens — I only want the most relevant sections."},{"title":"Extract Shopify page as skeleton outline","prompt":"Give me a skeleton outline of https://www.allbirds.com/pages/our-materials so I can quickly understand the page structure without reading the full content."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status instead of distilled content","max_tokens set below 20 is rejected as out of range","mode=budget without a query may return less focused results","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-heavy pages may yield poor extraction quality","Missing required 'url' parameter returns a validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget, wants BM25-ranked relevance filtering over a specific query, or needs structured/skeleton extraction rather than raw HTML. It is especially valuable when fetching documentation, competitive intelligence pages, or research articles where most HTML is noise. Prefer it over generic scrapers when token efficiency and LLM cost savings are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:58.760Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-semantic-html-pruner-web-url-distillation-api-faf9d16f"}