{"uid":"cap_FASc3Yh8463he4rJ-j_Kn","slug":"agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-control-738ac386","name":"AgentDiet Web 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)","url":"https://agentdiet.dev/v1?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_2XXEq_hgneznMe0kXeGZY","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 and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-focused excerpt within a strict token budget","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/accept-a-payment into Markdown using budget mode, focused on 'payment intent API', keeping it under 500 tokens.","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Fetch and distill https://openai.com/pricing into clean Markdown so I can read the key pricing tiers without burning through my context window."},{"title":"BM25-focused research excerpt","prompt":"Pull https://arxiv.org/abs/2305.11206 and give me only the sections relevant to 'chain-of-thought prompting' in budget mode, capped at 300 tokens."},{"title":"Structured data extraction from HTML","prompt":"I have this raw HTML from a product listing page — distill it in structured mode so I get the tables and metadata as clean JSON without all the navigation noise."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","HTML payload too large or malformed — distillation may fail or produce incomplete output","mode=budget with no query or max_tokens — BM25 filtering cannot execute without focus parameters","Invalid or expired payment — x402 payment required before content is returned","max_tokens set below 20 — rejected by schema validation","Idempotency key reused with different parameters — may return cached prior result"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost — especially when the target page is long, noisy, or ad-heavy. The BM25 budget mode is uniquely suited for precision extraction when you only care about a specific topic within a large document. Prefer it over raw HTTP fetching whenever token efficiency matters, or when you need structured JSON tables extracted from HTML rather than raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:23.747Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-control-e8a546c8"}