{"uid":"cap_c5HA17SGHPMy_UTKk7LbM","slug":"agentdiet-dev-agentdiet-web-distiller-d2effbe3","name":"AgentDiet Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/article-extractor)","url":"https://agentdiet.dev/v1/article-extractor?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_oda0NjNObSMYWJWEbwlsU","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 web URL (or raw HTML) and distills it into compact, agent-ready tokens with BM25 budget control across multiple output modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments/accept-a-payment into compact markdown, keeping it under 500 tokens and focusing on the setup steps?","exampleUseCases":[{"title":"Research article extraction for agent pipeline","prompt":"Grab the main article content from https://techcrunch.com/2024/05/01/openai-gpt5-launch and give it to me as clean markdown so I can feed it into my summarizer."},{"title":"Token-budget-constrained page reading","prompt":"Fetch https://docs.anthropic.com/en/docs/about-claude/models and distill it in budget mode, focused on 'model context window sizes', keeping it under 300 tokens."},{"title":"Structured data extraction from a web page","prompt":"Pull https://en.wikipedia.org/wiki/S%26P_500 and distill it in structured mode so I get the tables and metadata as JSON rather than raw text."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt), along with an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered content","Very large pages may exceed processing limits or increase latency","Raw HTML input that is malformed may yield poor distillation quality","Paywalled or JavaScript-rendered pages may not extract correctly","Missing required 'url' parameter returns a validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must minimize token usage — especially in agentic pipelines with strict context budgets. It is ideal over raw HTTP fetch when you need clean Markdown, structured JSON extraction, or BM25-ranked relevance filtering. Prefer it over generic scrapers when you need built-in ROI metrics showing exactly how many tokens were saved. Use the budget mode with a query when you only want the most relevant passages from a long page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:44.207Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-distiller-d2effbe3"}