{"uid":"cap_FDO8LEcq5KEKZo66xStgr","slug":"agentdiet-dev-agentdiet-semantic-html-pruner-8b2f53d3","name":"AgentDiet Semantic HTML Pruner","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":"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_q-3XE8SHznUm8ibLmT2If","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 a URL or raw HTML and distills it into compact, token-efficient agent-ready content using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact Markdown using budget mode with a focus query on 'payment intents' and a max token ceiling of 2000 tokens.","exampleUseCases":[{"title":"Summarize docs page for agent pipeline","prompt":"Grab the content from https://docs.anthropic.com/claude/reference and distill it into clean Markdown so I can feed it to my agent without blowing my token limit."},{"title":"BM25-focused excerpt for research query","prompt":"I need only the parts of https://en.wikipedia.org/wiki/Retrieval-augmented_generation that are relevant to 'vector databases' — use budget mode with a max of 1500 tokens so it fits in my context window."},{"title":"Structured data extraction from product page","prompt":"Pull https://www.apple.com/iphone-16-pro/ and extract it in structured mode so I get the specs, pricing, and metadata as clean JSON tables rather than raw HTML."}],"resultDescription":"Returns a distilled version of the target page in the requested format (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics showing raw vs. distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and a cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","URL blocked by robots.txt or bot protection may return empty or partial content","max_tokens too low (below 20) rejected with validation error","BM25 query provided without mode=budget may be ignored","Raw HTML too large may time out or be truncated","Payment failure (HTTP 402) if x402 payment is not configured correctly"],"whenToPreferThis":"Choose this endpoint when an agent needs to read web content but must minimize token usage and LLM costs — especially in multi-step pipelines where raw HTML would be prohibitively large. It is ideal when you need targeted extraction (BM25 budget mode with a query) rather than full-page content, or when you want structured tables/metadata instead of raw HTML. Prefer it over generic scraping tools when token budget management and ROI reporting are important to your agent's cost controls.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:00.143Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-semantic-html-pruner-8b2f53d3"}