{"uid":"cap_esUNyQtmxCDd6HdjD390R","slug":"agentdiet-dev-web-content-distillation-with-bm25-budget-control-3da556fe","name":"Web Content 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://agentdiet.dev/v1/pdf-extract)","url":"https://agentdiet.dev/v1/pdf-extract?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_sMTSpIx0kxIGFKUuVMhff","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 accepts raw HTML and distills it into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch https://docs.stripe.com/payments/payment-intents and distill it into markdown using budget mode with the query 'payment confirmation webhooks', keeping it under 1500 tokens.","exampleUseCases":[{"title":"Token-budget docs extraction for agent context","prompt":"Pull https://platform.openai.com/docs/guides/function-calling and distill it in budget mode focused on the query 'tool call format', with a max of 800 tokens — I need to fit it into a tight prompt window."},{"title":"Structured table extraction from a pricing page","prompt":"Fetch https://www.cloudflare.com/plans/ and distill it in structured mode so I get the pricing tiers and feature comparisons as clean JSON tables."},{"title":"Skeleton outline of a long article","prompt":"Take this raw HTML I'm pasting in and distill it into a skeleton outline mode — I just need the headings and section structure, not the full body text."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON, outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, compression ratio percentage, tokens saved, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — fetch fails with error","HTML too large or malformed — parsing may fail or produce degraded output","max_tokens too low (below 20) — rejected by schema validation","query missing when mode=budget — BM25 ranking cannot operate","Payment not provided or invalid — HTTP 402 returned blocking execution","Invalid mode enum value — request rejected","Idempotency key collision on a different payload — may return cached mismatched result"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM context window and want to minimize token usage and cost — especially when you need BM25-ranked relevance filtering to a specific query (budget mode), or when you want structured JSON tables or skeleton outlines rather than raw HTML dumps. Prefer it over generic scrapers when token economy and compression ROI reporting matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T00:35:11.852Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-web-content-distillation-with-bm25-budget-control-3da556fe"}