{"uid":"cap_wY5aJpnkSBR10mWFeW8oV","slug":"whale-momentum-agentdiet-dev-context-trimmer-bm25-budget-controlled-50eaf10d","name":"Context Trimmer: BM25 Budget-Controlled Web Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://whale-momentum.agentdiet.dev/v1/context-trimmer)","url":"https://whale-momentum.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_doWW7IeDwaWo8XMfIWuaC","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"whale-momentum.agentdiet.dev","brandSlug":"whale-momentum-agentdiet-dev-mpp","brandBaseUrl":"https://whale-momentum.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, token-budget-aware content using BM25 relevance ranking across multiple output modes.","exampleAgentPrompt":"Distill this page — https://docs.stripe.com/api/charges — into markdown using BM25 budget mode, focused on the query 'create a charge', and keep it under 2000 tokens.","exampleUseCases":[{"title":"Trim documentation to fit prompt","prompt":"Grab the content from https://platform.openai.com/docs/api-reference and compress it into a BM25 budget excerpt focused on 'function calling', keeping it under 1500 tokens so it fits in my context window."},{"title":"Extract structured data from webpage","prompt":"Take this HTML I pulled from a product listing page and distill it into structured JSON tables — pull out the pricing, specs, and metadata fields."},{"title":"Skeleton outline of long article","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page structure so I can see its main sections without loading all the tokens."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (markdown text, structured JSON, skeleton, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Optionally includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","HTML payload is empty or malformed — distillation returns minimal or empty data field","mode=budget used without a query or max_tokens — BM25 ranking cannot be applied","max_tokens set too low (below 20) — rejected by schema validation","Payment not provided or invalid — HTTP 402 returned requiring x402 USDC payment","Target URL is behind auth/paywall — fetched HTML may be a login page rather than content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to process a large webpage or HTML document but must stay within a token budget — especially useful for RAG pipelines, prompt construction, and cost reduction. The BM25 budget mode is uniquely suited for query-focused extraction where only the most relevant sections of a page are needed. Prefer this over generic scrapers when you need built-in token accounting, compression ratio metrics, and multiple output modes (markdown, structured, skeleton, budget).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:32.033Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-context-trimmer-bm25-budget-controlled-50eaf10d"}