{"uid":"cap_3u1wBn4tCgWM4RkVFhosK","slug":"defi-yield-agentdiet-dev-web-page-html-distillation-with-bm25-budget-bd14403a","name":"Web Page & HTML 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://defi-yield.agentdiet.dev/v1/context-diet)","url":"https://defi-yield.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_0_I5pjBOaJY8oIrWrZrjh","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into Markdown, structured JSON, an outline skeleton, or a BM25-ranked token-budget excerpt, returning compression ROI metrics.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into Markdown, keeping it under 1500 tokens — focus the BM25 budget on 'payment intents' so I only get the most relevant sections.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Grab https://docs.openai.com/api-reference and distill it to clean Markdown capped at 2000 tokens, using BM25 focused on 'chat completions' — I need to fit it into my agent's context window without burning tokens."},{"title":"Structured data extraction from landing page","prompt":"Distill https://linear.app/pricing into structured JSON tables so I can see their pricing tiers and features in a clean format without all the surrounding HTML noise."},{"title":"Skeleton outline of a long article","prompt":"Take this raw HTML I'm pasting in and give me a skeleton outline of its headings and key sections — I want to understand the document structure before deciding which parts to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested mode (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, tokens saved, ROI multiplier, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML content is empty or unparseable — distillation returns minimal or empty data object","mode=budget with no query provided — BM25 ranking may fall back to generic truncation","max_tokens set below minimum of 20 — validation error returned","Rate limit or payment failure — HTTP 402 or 429 response","URL requires JavaScript rendering not supported by server-side fetch — content may be incomplete"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before feeding it to an LLM, especially when you have a strict context budget or want BM25-ranked relevance filtering around a specific query. It is particularly valuable in agentic pipelines where fetching raw HTML would exceed context limits or inflate LLM costs. Prefer it over generic scrapers when you need compression ROI metrics or multiple distillation modes (Markdown, structured, skeleton, budget).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:34.305Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-page-html-distillation-with-bm25-budget-bd14403a"}