{"uid":"cap_-8iTV5cAadO2GVpIpAEzp","slug":"agentdiet-dev-agentdiet-context-diet-url-html-distillation-with-bm25-19a0de6c","name":"AgentDiet Context Diet – URL/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://agentdiet.dev/v1/context-diet)","url":"https://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_OGwxdBe8h288OC8kfcFi3","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, a skeleton outline, or a BM25-ranked token-budget excerpt, returning ROI proof of tokens saved.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into budget mode focused on 'payment intents' with a max of 500 tokens, so I can stay within my context window.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Grab https://docs.openai.com/api-reference and distill it into markdown mode so I can feed the key content to my agent without blowing out the context window."},{"title":"BM25 focused excerpt from long article","prompt":"I need just the parts of https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) that are relevant to 'attention mechanism' — use budget mode with a 300 token ceiling."},{"title":"Structured data extraction from raw HTML","prompt":"I have the raw HTML of a pricing page — can you distill it into structured mode to pull out the tables and metadata so I can compare plans programmatically?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing 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 is unreachable or returns non-200 — fetch fails with an error status","max_tokens set below 20 — validation error on the integer minimum","mode=budget used without providing a query — BM25 ranking has no focus term","Raw HTML provided alongside a URL — may conflict or be ignored depending on implementation","Rate limit or payment failure via x402 — billing error returned","Malformed or non-HTML URL (e.g. PDF, binary) — distillation may produce empty or garbled output"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and use web content but must stay within a token budget or minimize LLM inference costs. It is especially valuable over raw web scraping when you need BM25-ranked relevance filtering, clean Markdown conversion, or structured extraction from messy HTML — and when you want quantified proof of tokens saved. Prefer it over generic scrapers when operating in cost-sensitive or context-window-constrained pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:01.500Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-context-diet-url-html-distillation-with-bm25-19a0de6c"}