{"uid":"cap_34CZiyGKM8HNKoL8_FAws","slug":"agentdiet-dev-agentdiet-web-distillation-api-63e44d86","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/pdf-extract)","url":"https://agentdiet.dev/v1/pdf-extract?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_0au0aGmDK9FvT_W0iJAeA","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 a URL or raw HTML and compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments/accept-a-payment and distill it into compact markdown, keeping it under 2000 tokens and focusing on the BM25 query 'accept payment intent'.","exampleUseCases":[{"title":"Summarize documentation for coding agent","prompt":"Grab the React Router v6 docs at https://reactrouter.com/en/main/start/overview and distill them into structured markdown under 1500 tokens so I can use them in my coding context."},{"title":"Extract pricing table from competitor page","prompt":"Pull the pricing page at https://openai.com/pricing and return it as structured JSON tables so I can compare their tiers programmatically."},{"title":"BM25-focused excerpt for RAG pipeline","prompt":"Fetch https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and extract only the sections most relevant to 'cold start latency' in budget mode with a max of 800 tokens."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), 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 hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 — distillation cannot proceed","Invalid or malformed URL string — request rejected","Token budget too low (below 20) — validation error","HTML payload too large — may timeout or be truncated","BM25 query missing when mode=budget — incomplete results","Payment failure via x402 — endpoint returns 402 with payment details","Cached stale content returned for dynamic pages"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content into an LLM pipeline without blowing your context window. It is especially valuable when you need BM25-ranked relevance filtering (mode=budget with a query) to extract only the sections pertinent to your task, or when you want structured JSON tables/metadata instead of raw HTML. Prefer it over raw fetch+parse approaches when token cost and context efficiency matter, and when you want built-in ROI metrics proving the compression value.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:44:48.174Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distillation-api-640e00c8"}