{"uid":"cap_7ELQNxXW17QI4DRMweuGQ","slug":"agentdiet-dev-agentdiet-token-optimizer-url-html-distiller-with-bm25-e83a8b6a","name":"AgentDiet Token Optimizer — URL/HTML Distiller 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://agentdiet.dev/v1/token-optimizer)","url":"https://agentdiet.dev/v1/token-optimizer?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_347URGMKlcrMKToNlATku","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a webpage URL or raw HTML into compressed Markdown, structured JSON, skeleton outlines, or BM25-scored token-budget excerpts to reduce LLM context costs","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown and keep it under 1500 tokens, focusing on payment integration steps using budget mode with a BM25 query of 'payment integration'.","exampleUseCases":[{"title":"Token-budget web research for agents","prompt":"Fetch https://openai.com/pricing and compress it to under 800 tokens using budget mode with the query 'GPT-4 token pricing' — I need just the relevant pricing info for my agent pipeline."},{"title":"Structured table extraction from docs","prompt":"Distill https://docs.anthropic.com/claude/reference/models into structured JSON tables so I can see model names, context windows, and pricing in a clean format."},{"title":"HTML skeleton for long-form pages","prompt":"I have this raw HTML from a Wikipedia article — can you give me a skeleton outline of its sections so I know what's in it without burning my full context window?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may produce minimal output","Token budget (max_tokens) set too low for meaningful content extraction","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — returns 402 with payment details","Target URL blocks bots or requires authentication — fetch fails silently or partially"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a strict token budget or minimize LLM API costs. It is especially valuable for agentic pipelines that repeatedly fetch external URLs, for RAG systems needing clean Markdown, or when a specific topic focus (via BM25 query) should drive which portion of a page is retained. Prefer it over raw web scrapers when token efficiency and cost tracking (ROI proof) are required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:00.518Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-token-optimizer-url-html-distiller-with-bm25-e83a8b6a"}