{"uid":"cap_lNM5vUVOpSnqT2jHAny09","slug":"llms-generator-agentdiet-dev-context-bloat-eliminator-url-html-d87ef1bd","name":"Context Bloat Eliminator — URL/HTML 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://llms-generator.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://llms-generator.agentdiet.dev/v1/context-bloat-eliminator?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_iXvUsqB9tusBKI4CUXLS5","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton outline, or BM25-ranked token-budget excerpt to eliminate context bloat for LLM pipelines","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean Markdown using budget mode, focusing on 'payment intents API' and keeping it under 800 tokens?","exampleUseCases":[{"title":"LLM pipeline token budget enforcement","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with a max of 500 tokens, focused on the query 'rate limits', so I can pass just the relevant section to my model."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it into structured JSON so I can compare their pricing tiers programmatically — here's the HTML: <html>...</html>"},{"title":"Documentation skeleton for agent navigation","prompt":"Distill https://docs.github.com/en/rest into a skeleton outline mode so I can see the high-level structure of the REST API docs without all the detail."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked 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 — giving the agent measurable proof of context savings. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is empty or malformed — distillation may fail or return minimal output","max_tokens set too low relative to content — may produce truncated or empty budget excerpts","BM25 query provided without mode=budget — query parameter may be ignored","Rate limiting or payment failure (x402) — call fails with 402 or 429 response","Very large pages may exceed fetch timeout — latency spikes or timeout errors"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before feeding it to an LLM, especially when working within strict context window budgets. The BM25 budget mode is uniquely valuable when you have a specific query and want only the most relevant passages from a long page. Prefer this over generic scrapers when you need measurable compression ROI (tokens saved, cost saved) and multiple output modes (Markdown, structured JSON, skeleton, budget). It is especially well-suited for agentic pipelines that process many URLs and need deterministic token ceilings.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:31.505Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-context-bloat-eliminator-url-html-d87ef1bd"}