{"uid":"cap_1u7H4wCzpdfUuNqc1p689","slug":"serp-extract-agentdiet-dev-distill-url-or-html-with-bm25-budget-control-d9536b23","name":"Distill URL or HTML 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://serp-extract.agentdiet.dev/v1/prompt-compress)","url":"https://serp-extract.agentdiet.dev/v1/prompt-compress?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_qrM_QuuJN1B3-VbjzTE0V","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and compresses it into a token-efficient representation using BM25 ranking with a strict token budget ceiling","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 1500 tokens.","exampleUseCases":[{"title":"LLM cost reduction for research","prompt":"Grab the content from https://openai.com/research/gpt-4 and compress it into budget mode focused on 'safety evaluation', capped at 1000 tokens — I want to feed it into my pipeline without blowing the context window."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it in structured mode so I get clean JSON tables of their pricing tiers and features — here's the HTML: <html>...</html>."},{"title":"Skeleton outline for site audit","prompt":"Fetch https://docs.anthropic.com/claude and return a skeleton outline of the page structure so I can understand how their documentation is organized without reading the full content."}],"resultDescription":"Returns a data object containing the distilled content (markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt), plus an roi_proof block with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","HTML payload is malformed — distillation may be incomplete or empty","max_tokens set below minimum of 20 — rejected with validation error","query missing when mode=budget — BM25 ranking cannot proceed","Rate limiting or payment failure via x402 — request blocked","Idempotency-Key collision with different parameters — may return cached mismatched result"],"whenToPreferThis":"Choose this endpoint when you need to compress a specific URL or raw HTML into a token-budget-constrained excerpt using BM25 relevance ranking — especially when you have a focused query topic and a strict token ceiling. It is ideal for LLM pipeline cost reduction where you want to feed only the most relevant page content into a downstream model. Prefer it over generic web scrapers when you need quantified ROI metrics (tokens saved, compression ratio) alongside the distilled content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:15.105Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-distill-url-or-html-with-bm25-budget-control-d9536b23"}