{"uid":"cap_sjLbM6VsbKhh78SW-Kczt","slug":"agentdiet-dev-agentdiet-web-distillation-api-aa73dcd3","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/rag-chunk)","url":"https://agentdiet.dev/v1/rag-chunk?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_35WLxkA_Gimm5OPyCe9L7","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 URL or raw HTML into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill this URL into clean markdown within 500 tokens, focusing on pricing information: https://stripe.com/pricing — I need a compact version I can drop into my LLM context.","exampleUseCases":[{"title":"RAG pipeline context compression","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured JSON tables so I can use it as a compact knowledge chunk in my RAG pipeline without blowing my context window."},{"title":"Budget-capped research extraction","prompt":"Pull down https://techcrunch.com/2024/01/15/ai-funding-report and extract only the parts relevant to 'venture capital AI funding', keeping it under 300 tokens."},{"title":"Webpage skeleton for agent planning","prompt":"Get me a skeleton outline of https://www.ycombinator.com/companies so my agent can understand the page structure without loading the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), along with an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","Missing required 'url' parameter returns 400 validation error","mode=budget without 'query' may return unfiltered content","max_tokens below 20 rejected by schema validation","Private or bot-blocked pages may return empty or partial content","Payment failure via x402 may block response if credits exhausted"],"whenToPreferThis":"Choose this endpoint when you need to compress a live webpage or raw HTML into a token-efficient format before passing it to an LLM, especially when operating under strict context-window constraints. It is ideal for RAG pipelines, agent browsing tasks, or any workflow where full HTML is too verbose. The BM25 budget mode makes it uniquely suited for query-focused extraction at a fixed token ceiling — a feature rarely found in generic scrapers.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:14.749Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-api-640e00c8"}