{"uid":"cap_7sMkDZYiv3mtaY-nvhlZn","slug":"company-enrich-agentdiet-dev-web-url-html-distiller-with-bm25-budget-404569ba","name":"Web URL & HTML Distiller 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://company-enrich.agentdiet.dev/v1/spa-markdown-reader)","url":"https://company-enrich.agentdiet.dev/v1/spa-markdown-reader?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_-CSI7wtYMRX3-J_fdFfNE","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.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":"Fetch the page at https://stripe.com/docs/payments/checkout and distill it into clean Markdown using budget mode, focused on 'payment integration steps', with a max of 2000 tokens.","exampleUseCases":[{"title":"Token-efficient documentation reading","prompt":"Go to https://docs.openai.com/api-reference and distill it into Markdown using budget mode with a focus query on 'authentication and rate limits', keeping it under 1500 tokens so I don't blow my context window."},{"title":"Structured data extraction from a product page","prompt":"Fetch https://www.example.com/products/widget-pro and distill it in structured mode so I get the tables, metadata, and key specs as JSON rather than raw HTML."},{"title":"Skeleton outline of a long article","prompt":"I need a high-level skeleton outline of this article — https://a16z.com/ai-agents-2024 — just the headings and subheadings, nothing more, so I can decide which sections to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton headings, or BM25-ranked excerpt), plus an roi_proof block showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing info.","failureModes":["URL is unreachable or returns non-200 — distillation fails with fetch error","Raw HTML is empty or malformed — output may be sparse or empty","max_tokens set below minimum of 20 — rejected with validation error","query omitted when mode=budget — BM25 focus unavailable, falls back to full distillation","SPA JavaScript-heavy page fails to render fully — content may be incomplete","Payment not provided or insufficient — HTTP 402 returned with payment requirements"],"whenToPreferThis":"Choose this endpoint when you need to read a webpage or HTML blob with strict token constraints — especially when passing content to an LLM and need to minimize token cost. It is specifically suited for BM25-focused extraction (retrieving only the most query-relevant content), structured extraction of tables and metadata, or skeleton outlining. Prefer it over raw HTTP fetching when compression ratio and cost savings matter, or when the target page is a SPA that requires JavaScript rendering.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:31.537Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-url-html-distiller-with-bm25-budget-404569ba"}