{"uid":"cap_vzroRX_-dMB3FoQx5hn36","slug":"hn-pulse-agentdiet-dev-rag-token-diet-web-url-distiller-aec245ce","name":"RAG Token Diet – Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/v1/rag-token-diet)","url":"https://hn-pulse.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 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_BBnyedecSg9OAYfw63mPk","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, keeping it under 800 tokens and focused on the topic 'payment intents'.","exampleUseCases":[{"title":"Budget-capped RAG ingestion for docs","prompt":"Fetch https://docs.openai.com/api-reference and distill it into at most 600 tokens in budget mode, focused on the query 'rate limits', so I can add it to my retrieval pipeline without blowing my context window."},{"title":"Structured data extraction from a news article","prompt":"Pull this article at https://techcrunch.com/2024/05/01/ai-funding-roundup and give me the structured tables and metadata — author, date, key entities — in structured mode."},{"title":"Skeleton outline of a long report","prompt":"Distill https://www.mckinsey.com/featured-insights/future-of-work/ai-report-2024 into a skeleton outline so I can quickly see the section headings and main topics without reading the whole thing."}],"resultDescription":"Returns a distilled representation of the webpage in the chosen mode (Markdown, structured JSON, skeleton, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio, and estimated LLM cost saved. Cache status and billing details are also included.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","HTML payload too large to process within the service limits","max_tokens set below minimum of 20 — validation error","BM25 query provided without mode=budget — query may be silently ignored","Payment not completed via x402 — HTTP 402 returned before content is served","Malformed URL string — schema validation failure on 'url' field"],"whenToPreferThis":"Choose this endpoint when you need to reduce a raw webpage or HTML blob to a compact, agent-usable form before feeding it into an LLM or vector store. It is especially valuable when token budget is a concern, offering BM25-focused excerpt mode to return only the most relevant content. Prefer it over generic scrapers when you need built-in compression metrics (ROI proof) or structured/skeleton extraction modes, and when you are operating in an HTTP 402 micropayment-native agentic pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:34.120Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-rag-token-diet-web-url-distiller-aec245ce"}