{"uid":"cap_DAVwjNGZuFL4aY3cbFqxl","slug":"serp-extract-agentdiet-dev-web-url-html-distillation-with-bm25-budget-e5618374","name":"Web URL & HTML Distillation 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/distill)","url":"https://serp-extract.agentdiet.dev/v1/distill?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_OhGWuK72ggqqZRhREM30v","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 and distills a URL or raw HTML into compact, token-efficient agent-ready content using BM25-ranked budget control and multiple output modes.","exampleAgentPrompt":"Fetch and distill https://stripe.com/docs/payments into compact markdown, using budget mode with the query 'payment intents' and a max of 500 tokens so I don't blow my context window.","exampleUseCases":[{"title":"Focused research from a live webpage","prompt":"Go to https://openai.com/research/gpt-4 and distill just the parts about model capabilities — use budget mode with the query 'capabilities and benchmarks' and cap it at 800 tokens."},{"title":"Structured data extraction from raw HTML","prompt":"I have this raw HTML from a product page — can you distill it into structured JSON tables so I can pull out the pricing tiers and tech specs without parsing it myself?"},{"title":"Token-efficient documentation reading","prompt":"Distill https://docs.anthropic.com/claude/reference/getting-started into markdown mode so my agent can read the full docs without using too many tokens."}],"resultDescription":"Returns a distilled version of the target content in the requested mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with ROI proof metrics (raw vs distilled token counts, compression ratio, LLM cost saved in USD), optional cache hit/miss status, and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","max_tokens set below 20 — rejected with validation error","BM25 query missing when mode=budget — may return unfiltered or error","Raw HTML is malformed — distillation may produce degraded output","Rate limiting or payment failure — 402 payment required response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read or process web content but must stay within token budget constraints, or when you want BM25-ranked relevance filtering rather than a full page dump. Ideal over generic scrapers when you need structured output modes (markdown, JSON tables, skeleton) and built-in token savings metrics. Particularly valuable when processing verbose documentation, product pages, or SERP results where most content is irrelevant noise.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:21.726Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-html-distillation-with-bm25-budget-e5618374"}