{"uid":"cap_KkgdyoCbg-1u8TgRUg17Q","slug":"serp-extract-agentdiet-dev-web-url-to-agent-ready-token-distiller-rag-81ac5698","name":"Web URL to Agent-Ready Token Distiller (RAG Token Diet)","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/rag-token-diet)","url":"https://serp-extract.agentdiet.dev/v1/rag-token-diet?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_Pv0hM0FDUzVcIqACibSdN","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 compresses a webpage or raw HTML into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 800 tokens and focusing on the query 'payment intents setup'?","exampleUseCases":[{"title":"RAG pipeline webpage compression","prompt":"Distill https://openai.com/research/gpt-4 into structured markdown so I can feed it into my RAG pipeline without blowing my token budget — keep it under 1000 tokens."},{"title":"Competitor pricing page extraction","prompt":"Fetch https://anthropic.com/pricing and pull out all the pricing tables and key metadata in structured mode so I can compare plans quickly."},{"title":"Focused doc excerpt for agent grounding","prompt":"I need just the most relevant excerpt from https://docs.aws.amazon.com/lambda/latest/dg/getting-started.html about 'cold start latency' — use budget mode with a max of 500 tokens."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML payload too large may exceed processing limits","mode=budget without a query or max_tokens may produce unfiltered output","Paywalled or JavaScript-heavy pages may return incomplete content","Insufficient x402 payment credentials result in 402 Payment Required","Rate limiting or SLA breach returns non-ok status"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress a live webpage into LLM-ready tokens with a measurable token budget — especially when context window space is scarce, you need BM25-focused excerpts on a specific query, or you want to quantify exactly how many tokens and dollars you saved. Prefer it over generic scrapers when you need structured output modes (markdown, tables, skeleton) and ROI proof of compression.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:40.230Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-to-agent-ready-token-distiller-rag-81ac5698"}