{"uid":"cap_V0CQ2mMaca61nEk7M4CId","slug":"json-repair-agentdiet-dev-web-url-html-context-trimmer-with-bm25-a6e5c83c","name":"Web URL & HTML Context Trimmer 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/context-trimmer)","url":"https://json-repair.agentdiet.dev/v1/context-trimmer?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_jJD_l5oj20vMeeQXpBh2a","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","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 a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget modes","exampleAgentPrompt":"Fetch the Stripe docs at https://stripe.com/docs/payments and distill them into compact markdown, keeping it under 2000 tokens focused on the query 'payment intents' using budget mode.","exampleUseCases":[{"title":"Compress docs to fit agent context","prompt":"Pull https://docs.openai.com/api-reference and distill it into structured markdown — I need it compact enough to fit in my agent's context window without blowing my token budget."},{"title":"BM25-focused budget excerpt for research","prompt":"Grab https://en.wikipedia.org/wiki/Retrieval-augmented_generation and give me only the parts most relevant to 'vector databases', capped at 500 tokens in budget mode."},{"title":"Skeleton outline of a long webpage","prompt":"Fetch https://stripe.com/docs and return just a skeleton outline of the page structure so I can understand what sections exist before diving deeper."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables/metadata, skeleton headings, or BM25-scored excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too small (max_tokens below 20) fails validation","BM25 query required but missing when mode=budget","Raw HTML too large may exceed processing limits","Paywalled or bot-protected pages may return empty or partial content","Missing required 'url' parameter returns a 400-style error"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before passing web content to an LLM — especially when dealing with large documentation pages, Wikipedia articles, or any URL whose raw HTML is too verbose for your context window. The BM25 budget mode is uniquely suited for query-focused extraction with a strict token ceiling, which no generic scraper provides. Prefer it over generic scrapers when you need measurable ROI metrics (compression ratio, cost saved) or when you need structured/skeleton modes in addition to plain markdown.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:16.813Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-context-trimmer-with-bm25-a6e5c83c"}