{"uid":"cap_Oo88Lkw7rEdaQnLq4w8AT","slug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-0690c4e6","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://company-enrich.agentdiet.dev/v1/context-diet)","url":"https://company-enrich.agentdiet.dev/v1/context-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_2eCPAJbBAYZFeRaQ--s7m","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-ranked token-budgeted excerpt to reduce LLM context costs.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown using budget mode, focused on 'payment intents', and keep it under 800 tokens.","exampleUseCases":[{"title":"LLM cost reduction for web research","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into markdown with BM25 budget mode focused on 'context length improvements', capped at 500 tokens, so I can pass it cheaply to my model."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from an e-commerce product page and distill it into structured JSON tables — I need prices, specs, and availability without all the nav and footer noise."},{"title":"Documentation skeleton for agent onboarding","prompt":"Pull https://docs.anthropic.com/claude/reference and return a skeleton outline of the page structure — I want headings and key sections only, no full content, so my agent can navigate it efficiently."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown text, structured JSON tables, skeleton outline, or BM25-ranked excerpt depending on mode), an ROI proof object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 HTTP status — fetch fails with error status","HTML payload too large or malformed — distillation returns partial or empty data","max_tokens set too low (below 20) — rejected with validation error","BM25 query missing when mode=budget — may return unfiltered or empty excerpt","Rate limit or payment failure via x402 — 402 response requiring payment","Invalid mode enum value — schema validation rejection"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM but want to minimize token usage and cost — especially when pages are long, bloated with boilerplate, or when only a query-relevant excerpt is needed. It is particularly strong for budget mode with BM25 ranking when you have a specific focus query and a strict token ceiling. Prefer it over raw fetching or generic scrapers when compression ROI metrics matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:50.071Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-distillation-with-bm25-budget-control-2d03f821"}