{"uid":"cap_pjL14WrSNN-1eGlj5Kx30","slug":"serp-extract-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-f9c6265f","name":"RAG Token Diet – BM25 Budget-Controlled Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (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":"POST","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_1MJ5mFuYeqTZWAwaQpZjv","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 a URL or raw HTML into compressed Markdown, structured JSON, or a BM25-ranked token-budget excerpt for RAG pipelines","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/accept-a-payment into a token-budgeted Markdown summary focused on 'payment intent lifecycle', capped at 500 tokens.","exampleUseCases":[{"title":"RAG pipeline token budget enforcement","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a BM25 excerpt about 'attention mechanism self-attention' with a hard cap of 300 tokens so I can pass it to my LLM without blowing the context window."},{"title":"Structured data extraction from a product page","prompt":"Take the HTML I'm pasting from this e-commerce product page and distill it into structured JSON — I need the tables, metadata, and specs pulled out cleanly."},{"title":"Cost-saving web content compression for agentic research","prompt":"Pull down https://openai.com/research/gpt-4 and distill it into clean Markdown, and tell me how many tokens you saved compared to the raw page so I can see the ROI."}],"resultDescription":"Returns a `data` object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an `roi_proof` block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional billing and cache hit/miss metadata.","failureModes":["URL is unreachable or returns non-200 — endpoint may error or return empty distillation","HTML payload is malformed or too large — distillation may be partial or fail","mode=budget used without providing a query — BM25 ranking cannot be applied","max_tokens set below minimum of 20 — validation error returned","Payment not processed (402 response) — call blocked until x402 payment is made","URL is valid but contains no extractable text (e.g. pure JS SPA) — output may be empty"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM and want to minimize token costs through intelligent compression. It is especially valuable when you have a strict token budget and a specific query focus (BM25 mode), or when you need structured extraction from messy HTML. Prefer this over raw fetch/scrape tools when you care about ROI proof, compression ratio reporting, and seamless RAG pipeline integration.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:40.538Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-f9c6265f"}