{"uid":"cap_ge_-ziUeq6wuhEfJBXxBW","slug":"serp-extract-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f4284d8a","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/context-compress)","url":"https://serp-extract.agentdiet.dev/v1/context-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_H8R7KpMI-leuhh2mublU_","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 compresses a URL or raw HTML into compact, token-efficient agent-ready content using selectable distillation modes including a BM25-focused budget mode with a strict token ceiling.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, but cap it at 800 tokens and focus the BM25 query on 'payment intents' so only the most relevant content makes it in.","exampleUseCases":[{"title":"Fit documentation into LLM context","prompt":"Pull the content from https://docs.openai.com/api-reference and compress it down to 1000 tokens max using budget mode, with the BM25 query set to 'function calling' so I only get the relevant parts."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from a product listing page and distill it into structured JSON tables with metadata — I need the pricing tiers, features, and company summary without all the bloat."},{"title":"Skeleton outline for research summarization","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page structure so I can quickly navigate what sections cover what topics."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25 budget excerpt depending on mode), an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — fetch error returned","max_tokens set below minimum of 20 — validation error","mode=budget used without providing a query — may return unfiltered or degraded output","Raw HTML too large to process within service limits — timeout or truncation","Invalid URL format provided — schema validation error","Target site blocks headless fetching — empty or error content returned"],"whenToPreferThis":"Choose this endpoint when you need to reduce token usage before passing web content to an LLM, especially when working with a strict context window or cost budget. The BM25 budget mode is uniquely suited for retrieving only the most query-relevant excerpt from a long page under a hard token ceiling. Prefer it over generic scrapers when you need compression metrics (ROI proof, tokens saved) alongside the content. Use the raw HTML input option when you have already fetched the page and just need distillation without a second fetch.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:36.057Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f4284d8a"}