{"uid":"cap__k9ZufmVPreUsC4oKEIBU","slug":"x402broker-com-web-distillation-with-bm25-budget-control-e955777d","name":"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://x402broker.com/api/diet)","url":"https://x402broker.com/api/diet?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_QDLbwM1MmejKQtEqHu_XX","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton outline, or BM25-focused excerpt within a strict token budget","exampleAgentPrompt":"Distill https://stripe.com/docs/api into clean Markdown using budget mode, focused on the query 'authentication', and keep it under 800 tokens.","exampleUseCases":[{"title":"LLM-ready webpage summarization","prompt":"Grab https://openai.com/research/gpt-4 and distill it into clean Markdown — I want to feed it to my model without wasting tokens on nav bars and footers."},{"title":"BM25-focused research excerpt","prompt":"Pull https://arxiv.org/abs/2305.10601 and give me only the sections most relevant to 'chain-of-thought prompting', capped at 600 tokens using budget mode."},{"title":"Structured data extraction from HTML","prompt":"I have some raw HTML from a product page — can you distill it into structured JSON tables so I can extract the pricing and specs without parsing it myself?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (Markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","Missing required 'url' field when 'html' is not provided returns a 400 validation error","mode=budget without a 'query' field may return unfiltered content","max_tokens below minimum of 20 returns a validation error","Paywalled or JavaScript-heavy pages may return incomplete or empty distillation","Payment failure via x402 returns HTTP 402 before processing begins"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content to an LLM while minimizing token usage and cost — especially when you need BM25-targeted excerpts (budget mode) to stay within a strict token ceiling. Prefer it over generic scrapers when you want built-in compression metrics (ROI proof), multiple distillation modes (Markdown/structured/skeleton/budget), and direct HTML input support without a separate fetch step.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:00.048Z","isFirstParty":false,"canonicalSlug":"x402broker-com-web-distillation-with-bm25-budget-control-85b7c1a4"}