{"uid":"cap_G2NLDLAOs62m-a5q7vtVd","slug":"serp-extract-agentdiet-dev-web-content-distiller-with-bm25-budget-956b9910","name":"Web Content Distiller 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/token-optimizer)","url":"https://serp-extract.agentdiet.dev/v1/token-optimizer?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_hDmIVULbmQpznkLiXnoO8","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 distills it into compact, token-efficient agent-ready content using BM25-ranked budget control","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/accept-a-payment into budget mode, focused on the query 'accept card payments', and cap it at 500 tokens so I can fit it into my LLM context cheaply.","exampleUseCases":[{"title":"Token-budget extraction for LLM context","prompt":"Fetch https://docs.anthropic.com/en/api/messages and distill it in budget mode with the query 'streaming responses', keeping it under 300 tokens so I can stuff it into my prompt without blowing my context window."},{"title":"Structured table extraction from a webpage","prompt":"Take the raw HTML from this pricing page and distill it in structured mode so I get the pricing tiers and feature tables back as clean JSON — here's the HTML: <html>...</html>"},{"title":"Skeleton outline for long documentation","prompt":"Give me a skeleton outline of https://nextjs.org/docs so I can see the high-level structure of the docs without reading thousands of tokens of content."}],"resultDescription":"Returns a data object containing the distilled content (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an roi_proof block showing 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":["Missing required 'url' field returns validation error","Invalid URL format causes fetch failure","mode=budget without a 'query' field may return unranked or degraded output","max_tokens below 20 rejected by schema validation","Raw HTML too large may cause timeout or truncation","Paywalled or JavaScript-rendered pages may return incomplete distillation","x402 payment failure returns 402 with payment instructions"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM — especially when you have a strict token budget or a specific focus query (BM25 mode). Prefer it over generic scrapers when you need ROI proof (tokens saved, compression ratio) alongside the distilled content. Use the budget+query mode when you only want the most relevant passages from a long page. Use structured mode when you need tables and metadata extracted as JSON rather than prose markdown.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:06.672Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-content-distiller-with-bm25-budget-956b9910"}