{"uid":"cap_n8N1KFlMmtLLH89VrCWXj","slug":"alpha-stream-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-58036ff5","name":"AgentDiet 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://alpha-stream.agentdiet.dev/v1/rag-token-diet)","url":"https://alpha-stream.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_32_6YZKKyuZP5zURtRmgC","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and compresses it into compact, agent-ready tokens using selectable distillation modes and BM25 budget control","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments into compact markdown, keeping it under 800 tokens and focusing on the query 'payment intents' using budget mode.","exampleUseCases":[{"title":"RAG pipeline token budget control","prompt":"Fetch https://openai.com/research/gpt-4 and distill it down to at most 500 tokens using budget mode, focused on the query 'context window improvements' — I need it tight enough to fit in my RAG pipeline without blowing my LLM token limit."},{"title":"Structured data extraction from a webpage","prompt":"Pull the content from https://en.wikipedia.org/wiki/Large_language_model and give me a structured JSON version with tables and metadata — I want it in structured mode so I can parse the key facts programmatically."},{"title":"Skeleton outline for quick page navigation","prompt":"Give me a skeleton outline of https://docs.anthropic.com/claude/reference/getting-started-with-the-api so I can quickly see the headings and structure without reading the whole page."}],"resultDescription":"Returns a distilled version of the webpage in the chosen mode (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with ROI proof metrics including raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache status (HIT/MISS) 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 suboptimal results","Pages behind authentication or paywalls cannot be fetched","Rate limiting or payment failure (HTTP 402) if USDC balance is insufficient","Malformed HTML input may produce incomplete distillation"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and token cost or context-window size is a concern. It is especially valuable when you have a strict token budget (use budget mode with a BM25 query), need structured extraction from messy HTML, or want a quick skeleton outline of a large page. Prefer this over raw web scraping tools when you need the content pre-processed and compressed rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:58.898Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-58036ff5"}