{"uid":"cap_2Eec0FnedIfWItF1KQvHh","slug":"json-repair-agentdiet-dev-web-distillation-with-bm25-budget-control-079ac2a2","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://json-repair.agentdiet.dev/v1/distill)","url":"https://json-repair.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":"$0.001000/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001000","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001000","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Kqn917uQ7agfgt1QLpG7W","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001000","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into markdown mode and tell me how many tokens you saved compared to the raw page.","exampleUseCases":[{"title":"Fit documentation into context window","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with the query 'rate limits' and a max of 500 tokens — I need just the rate-limit relevant parts to fit in my prompt."},{"title":"Extract structured tables from a financial page","prompt":"Distill https://finance.yahoo.com/quote/AAPL in structured mode so I get the key data tables and metadata as JSON rather than the full HTML."},{"title":"Summarize raw HTML from a scraped page","prompt":"I've got this raw HTML from a product listing page — can you distill it into clean markdown so I can read the important content without all the noise?"}],"resultDescription":"Returns a data object containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","Raw HTML provided is malformed or empty — distillation may produce minimal output","mode=budget used without a query parameter — BM25 focus cannot be applied","max_tokens set below 20 — rejected by schema validation","Paywalled or JavaScript-rendered pages may yield incomplete content","Payment via x402 fails — call is not executed"],"whenToPreferThis":"Choose this endpoint when you need to compress a webpage or raw HTML into a token-efficient form before feeding it to an LLM, especially when you want BM25-focused budget excerpts that surface only query-relevant content within a strict token ceiling. It is ideal for agents that need to read documentation, news articles, or data pages without blowing up context windows or LLM costs. Prefer it over generic scraping tools when token savings metrics and cost ROI reporting are needed alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T04:48:15.784Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-distillation-with-bm25-budget-control-079ac2a2"}