{"uid":"cap_OWp1csGlC1DKAojK6RubR","slug":"token-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-21f72f63","name":"Web 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/distill)","url":"https://token-intel.agentdiet.dev/v1/distill?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_2SWOJ9x2ANmjCroZrBBbW","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 and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compressed Markdown using budget mode, focus the BM25 query on 'payment intents', and cap the output at 500 tokens.","exampleUseCases":[{"title":"LLM-friendly webpage summarization","prompt":"Grab https://openai.com/research/gpt-4 and distill it into clean Markdown so I can drop it into my context window without blowing my token budget."},{"title":"Focused content extraction for RAG pipeline","prompt":"Distill https://docs.anthropic.com/claude/reference in budget mode with the query 'tool use and function calling', keeping the output under 800 tokens so only the most relevant sections come through."},{"title":"Structured data extraction from raw HTML","prompt":"I have a raw HTML blob from a product page — distill it into structured JSON tables including any pricing tiers and metadata without fetching anything from the web."}],"resultDescription":"Returns a JSON object containing: a 'data' field with the distilled content (Markdown string, structured JSON, skeleton, or BM25 excerpt depending on mode); an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional cache metadata (HIT/MISS, latency_ms); and billing details including fee_charged_usd.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","Invalid mode enum value — request rejected with validation error","max_tokens set below minimum of 20 — rejected","Both url and html omitted — url is required so request fails schema validation","BM25 query provided without mode=budget — query may be silently ignored","Payment failure via x402 — 402 response if payment is not completed","Target page is JavaScript-heavy SPA — distillation quality may degrade"],"whenToPreferThis":"Choose this endpoint when you need to ingest web content into an LLM context while minimizing token usage and cost — especially when a strict token budget is required (mode=budget with BM25 ranking). Prefer it over raw web fetchers when you need compression metrics (roi_proof) to justify distillation ROI. Use the structured mode when you need tables and metadata extracted, or skeleton mode for quick outline navigation. It is particularly well-suited for agent pipelines that repeatedly read documentation or research pages and need predictable, budget-controlled outputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:22.454Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-21f72f63"}