{"uid":"cap_ak4Z9-_rn39zWrtAvoonh","slug":"json-repair-agentdiet-dev-web-url-html-distiller-with-bm25-budget-dea55f6d","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://json-repair.agentdiet.dev/v1/context-trimmer)","url":"https://json-repair.agentdiet.dev/v1/context-trimmer?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_gBlo_9r-rbIHuvc7Uu1D2","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 accepts raw HTML and distills it into compact, agent-ready tokens with optional BM25 relevance-focused budget trimming","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into compact markdown using budget mode, focused on 'payment intents', keeping it under 1500 tokens so it fits in my context window.","exampleUseCases":[{"title":"Stripe docs for agent context","prompt":"Grab the Stripe docs page at https://stripe.com/docs/api and distill it down to under 1000 tokens in budget mode, focused on the query 'webhooks', so I can feed just the relevant bits to my agent."},{"title":"Competitor pricing page analysis","prompt":"Distill https://openai.com/pricing into structured mode so I get clean tables and metadata I can compare against other AI provider pricing."},{"title":"Raw HTML cleanup for LLM input","prompt":"I have a raw HTML blob from a scraped article — distill it into clean markdown skeleton mode so I can pass just the outline and headings to my LLM without wasting tokens on boilerplate."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-trimmed excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, 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 status — fetch fails with error status","max_tokens set too low (below 20) — validation error returned","mode=budget used without a query parameter — may return unfiltered or error","HTML input is empty or malformed — distillation returns minimal or error output","Payment not included or insufficient — HTTP 402 returned blocking the call","Rate limits exceeded — service throttles or rejects the request"],"whenToPreferThis":"Choose this endpoint when you need to reduce a webpage or HTML blob to fit within an LLM context window, especially when you want BM25-driven relevance filtering to keep only the most query-relevant tokens. It is uniquely suited for agentic pipelines where token cost and context size matter — the roi_proof response tells you exactly how many tokens and dollars were saved. Prefer this over generic scrapers when you need multiple distillation modes (markdown, structured, skeleton, budget) and built-in token budget enforcement.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:14.217Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-distiller-with-bm25-budget-4226b0e2"}