{"uid":"cap_DVIm47loYFW1MZFjYtqjh","slug":"token-intel-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-5345e6c4","name":"URL to Markdown 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/url-to-markdown)","url":"https://token-intel.agentdiet.dev/v1/url-to-markdown?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_SnVomsvaaGgS6NX80-EVC","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 converts it to distilled Markdown, structured JSON, or a BM25-ranked token-budget excerpt, reporting token savings and compression metrics.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into markdown using budget mode, focused on 'payment intents', keeping it under 2000 tokens?","exampleUseCases":[{"title":"Fit docs page into context window","prompt":"Grab https://docs.openai.com/api-reference and distill it in budget mode with the query 'function calling' and a max of 1500 tokens — I need to feed it to a model without blowing my context limit."},{"title":"Extract structured tables from a pricing page","prompt":"Take https://aws.amazon.com/ec2/pricing/ and run it through structured distillation mode so I get the pricing tables as JSON instead of a wall of HTML."},{"title":"Convert raw HTML email to markdown","prompt":"I have this raw HTML newsletter content — can you distill it directly into clean markdown without fetching anything? Here's the HTML: <html>...</html>"}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","HTML input is malformed or empty — distillation returns minimal or empty output","max_tokens set too low (below 20) — validation error returned","query field omitted when mode=budget — BM25 ranking cannot be applied","Rate limiting or payment failure via x402 — 402 Payment Required response","Target URL blocks headless fetchers — returns empty or anti-bot page content"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM and want to minimize token usage and cost — especially when using budget mode with a BM25 query to extract only the most relevant excerpt from a long page. It is distinctly useful over generic scrapers because it returns explicit token savings metrics and compression ratios alongside the content, making it ideal for cost-aware agentic pipelines. Prefer it over raw HTML fetchers when you need clean Markdown or structured JSON output rather than raw DOM.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:08.017Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-5345e6c4"}