{"uid":"cap_zuCUHeeSxZJGJtdaSE-CM","slug":"agentdiet-dev-agentdiet-web-url-distiller-592eddcc","name":"AgentDiet Web URL 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/paywall-clean-extract)","url":"https://agentdiet.dev/v1/paywall-clean-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_2fm8rMy2BsAgbDm1J0AHa","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 webpage URL (or raw HTML) into compact, token-efficient agent-ready content using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/checkout into compact markdown so I can read it without burning my token budget — use budget mode with the query 'checkout integration' and cap it at 500 tokens.","exampleUseCases":[{"title":"Research page for a coding agent","prompt":"Pull the content from https://docs.anthropic.com/claude/reference/getting-started-with-the-api and distill it into clean markdown so I can use it in my context window without wasting tokens."},{"title":"Focused budget extraction for a question","prompt":"I need to find the pricing section on https://openai.com/pricing — distill it in budget mode with the query 'GPT-4 cost per token' and keep it under 300 tokens."},{"title":"Structured data from a product page","prompt":"Fetch https://www.apple.com/iphone/ and extract a structured JSON summary with the key product specs and metadata so I can compare it to other listings."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or JavaScript-rendered pages may return incomplete content","max_tokens below minimum (20) will be rejected","BM25 query with no matching content may return minimal excerpt","Rate limiting or payment failure (402) if agent wallet is not funded","HTML payload too large may time out or be truncated"],"whenToPreferThis":"Choose this endpoint when an agent needs to read a webpage but wants to minimize LLM token consumption and cost. It is especially useful when the target page is long or noisy, when only a specific section is needed (use budget mode + query), or when structured metadata extraction is required. It outperforms generic scrapers by providing built-in token budget control, ROI metrics, and multiple distillation modes tailored for agent workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:58.237Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-url-distiller-47b37abc"}