{"uid":"cap_hVR4d2BE-pbDpLTiPrXsh","slug":"agentdiet-dev-agentdiet-web-distillation-api-640e00c8","name":"AgentDiet Web Distillation API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/web-scrape)","url":"https://agentdiet.dev/v1/web-scrape?utm_source=zero.xyz","method":"GET","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__vUQ1jp5APyg4QG58NSQ4","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 compresses a web page or raw HTML into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown and keep it under 800 tokens, focusing on the query 'payment intents' using budget mode.","exampleUseCases":[{"title":"Token-efficient research on competitor page","prompt":"Fetch https://openai.com/pricing and distill it into structured mode so I can see the pricing tables without burning thousands of tokens."},{"title":"BM25-focused excerpt for RAG pipeline","prompt":"Grab https://docs.anthropic.com/claude/reference and extract only the parts relevant to 'tool use' in budget mode with a max of 500 tokens."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into skeleton mode so I get the heading structure and key sections without all the body text."}],"resultDescription":"Returns a 'data' object containing distilled content in the chosen format (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","URL blocked by robots.txt or anti-bot protections","max_tokens below minimum of 20 returns validation error","mode=budget without a query may return unfiltered or empty excerpt","Payment failure via x402 returns 402 with payment details","HTML too large for processing may be truncated or rejected","Malformed HTML input may produce incomplete distillation"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web content but must operate within a token budget — especially for LLM pipelines where raw HTML or verbose pages would be too expensive to process. Prefer it over generic scrapers when you need BM25-ranked excerpts, structured table extraction, or skeleton outlines rather than raw HTML dumps. Best suited for agents doing research, RAG enrichment, or competitive intelligence on live web pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:25.334Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-api-640e00c8"}