{"uid":"cap__50QX4aa11y_tfd96tENO","slug":"token-intel-agentdiet-dev-rag-diet-url-html-distillation-with-bm25-13742709","name":"RAG Diet — URL & HTML Distillation with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://token-intel.agentdiet.dev/v1/rag-diet)","url":"https://token-intel.agentdiet.dev/v1/rag-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_0RM05OUS5mmgCAvBhwt7F","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compressed Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown using budget mode focused on the query 'payment intents', capped at 2000 tokens — I want to see how many tokens we save compared to the raw page.","exampleUseCases":[{"title":"RAG pipeline cost reduction","prompt":"Fetch https://docs.openai.com/guides/embeddings and distill it down to a 1500-token budget excerpt focused on the query 'embedding dimensions' — I want the BM25-relevant sections only so I'm not blowing my context window."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it into structured JSON tables so I can compare their pricing tiers without reading through all the noise."},{"title":"Documentation skeleton for agent memory","prompt":"Distill https://docs.github.com/en/rest into a skeleton outline mode — I just need the high-level structure of their REST API docs, not the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache hit/miss status with latency_ms and billing info showing fee_charged_usd.","failureModes":["URL unreachable or returns non-200 — distillation cannot proceed","Invalid or empty HTML provided when using html parameter — returns error status","max_tokens below minimum of 20 — validation error","BM25 query omitted when mode=budget — may return unfiltered or error response","Rate limiting or payment failure via x402 — HTTP 402 returned requiring USDC micropayment","Malformed URL string — schema validation failure"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window but want to minimize token usage and cost — especially for RAG pipelines, agentic browsing, or document Q&A. The BM25 budget mode is uniquely suited for query-focused extraction with a hard token ceiling, making it ideal when you have a specific question about a long document. Prefer this over generic scrapers when you need built-in compression metrics (roi_proof) and multiple distillation modes (markdown, structured, skeleton, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:21.727Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-rag-diet-url-html-distillation-with-bm25-13742709"}