{"uid":"cap_sih-SyBVKiTNmaO8aGbjS","slug":"domain-osint-agentdiet-dev-web-url-to-agent-ready-token-distiller-99c1ebb4","name":"Web URL to Agent-Ready Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://domain-osint.agentdiet.dev/v1/clean-html)","url":"https://domain-osint.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_zTJ_bxW2s7YVqMaRp7gjI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a webpage URL (or raw HTML) into compact, LLM-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, using budget mode with the query 'payment intents' and a max of 500 tokens so I don't blow my context window?","exampleUseCases":[{"title":"Research doc summarization for agent","prompt":"Pull the content from https://docs.openai.com/api-reference and distill it into structured markdown so my agent can read it without hitting token limits."},{"title":"BM25-focused competitor page extraction","prompt":"Fetch https://www.competitor.com/pricing and extract only the sections relevant to 'enterprise plan pricing' using budget mode with a ceiling of 300 tokens."},{"title":"Raw HTML cleanup for LLM pipeline","prompt":"I have this raw HTML blob from a scraped product page — can you run it through skeleton mode to get just the structural outline so I can parse it programmatically?"}],"resultDescription":"Returns distilled content in one of four formats (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with ROI proof metrics including raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Optionally includes billing details and cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered output","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-rendered pages may return incomplete content","Token budget too small (below 20) rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token consumption and cost. It is especially useful when you have a strict token budget (use mode=budget with a BM25 query), want structured or skeleton output rather than raw HTML, or are building an agent pipeline that reads many URLs and needs consistent, compressed, clean output. Prefer it over raw HTTP fetches when context window efficiency matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:45.706Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-to-agent-ready-token-distiller-99c1ebb4"}