{"uid":"cap_RnZeKRd2YhbHE2PrmMGrE","slug":"serp-extract-agentdiet-dev-web-url-token-optimizer-distiller-c506cd1b","name":"Web URL Token Optimizer & Distiller","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/token-optimizer)","url":"https://serp-extract.agentdiet.dev/v1/token-optimizer?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_dzhbS9wHN__se0iRZ5crY","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills any webpage URL (or raw HTML) into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intents setup'?","exampleUseCases":[{"title":"Fit documentation page into context window","prompt":"I need to feed the Stripe docs at https://stripe.com/docs/api into my agent but the page is huge — can you compress it to under 1500 tokens in budget mode, focusing on the query 'authentication API keys'?"},{"title":"Extract clean markdown from news article","prompt":"Please distill https://techcrunch.com/2025/01/15/openai-latest-news into clean markdown so my agent can summarize it without burning through a ton of tokens."},{"title":"Structured table extraction from product page","prompt":"Pull https://aws.amazon.com/ec2/pricing/ in structured mode so I get the pricing tables and metadata as clean JSON instead of the full bloated HTML."}],"resultDescription":"Returns a 'data' object containing distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus 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 cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","max_tokens below minimum of 20 rejected with validation error","mode=budget without a query parameter may return unfiltered content","Payment failure via x402 blocks the request","Rate limits may apply per agent_id","Very large HTML pages may exceed processing limits","builtin:// scheme only valid for documented built-in targets like stripe-docs"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web pages or process HTML but must stay within a token budget or minimize LLM costs. It is especially valuable when processing documentation pages, news articles, or data-heavy pages where raw content would be too large. Prefer over generic scrapers when you need BM25-filtered excerpts relevant to a specific query, or when you want structured/skeleton extraction modes rather than raw text. Ideal for agentic pipelines where LLM input cost is a concern and you want measurable ROI proof of compression.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:01.165Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-token-optimizer-distiller-c506cd1b"}