{"uid":"cap_1H3Gn_H4VPAye3MVq4hKD","slug":"token-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-d911f7d9","name":"Web 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://token-intel.agentdiet.dev/v1/clean-html)","url":"https://token-intel.agentdiet.dev/v1/clean-html?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_X5dJh9JabJ0RLpYPPouv_","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 web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and optional BM25-guided token budgeting","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown, keeping it under 2000 tokens and focusing on the authentication section?","exampleUseCases":[{"title":"LLM cost reduction for web research","prompt":"Fetch https://docs.openai.com/api-reference and distill it into budget mode, focusing on the 'chat completions' section with a max of 1500 tokens — I want to save on LLM costs when passing this to a downstream model."},{"title":"Structured data extraction from landing page","prompt":"Take the HTML from this product page at https://www.anthropic.com/claude and extract it in structured mode so I get the tables and metadata in a clean JSON format."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into skeleton mode so I get just the section headers and outline structure without all the body content."}],"resultDescription":"Returns a distilled version of the target webpage or HTML payload in the requested mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML payload too large may exceed processing limits","BM25 budget mode requires both query and max_tokens to be meaningful","max_tokens set below 20 is rejected by schema validation","Payment failure via x402 blocks the request","Cached responses may be stale for rapidly changing pages"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to process web pages but must stay within token budgets or reduce LLM inference costs — especially when the raw HTML is noisy or large. The BM25 budget mode makes it uniquely suited for targeted extraction when only a specific topic or section of a page is relevant. Prefer it over generic scrapers when you need ROI metrics on token compression or need structured/skeleton output formats beyond raw markdown.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:41.748Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-d911f7d9"}