{"uid":"cap_ePyGQndgxzaiYiWfNtkAU","slug":"whale-momentum-agentdiet-dev-web-url-to-agent-ready-token-distiller-920545e1","name":"Web URL to Agent-Ready Token Distiller (RAG Token Diet)","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/rag-token-diet)","url":"https://whale-momentum.agentdiet.dev/v1/rag-token-diet?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_JWX0lw-19vGlrUuNOLdrp","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 raw HTML and distills it into compact, token-efficient content using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, staying under 800 tokens, and focus the BM25 budget on 'payment intents'?","exampleUseCases":[{"title":"RAG pipeline token budget control","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into budget mode focused on 'context window', keeping the output under 500 tokens so I can fit it into my retrieval pipeline."},{"title":"Structured data extraction from docs page","prompt":"Can you pull https://docs.stripe.com/api and return it in structured mode so I get the tables and metadata in clean JSON rather than raw HTML?"},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model in skeleton mode — I just need the section headers and key outline, not the full text."}],"resultDescription":"Returns a distilled version of the target webpage or HTML in the requested mode (markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt), plus an roi_proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a cache status indicator.","failureModes":["URL is unreachable or returns non-200 — distillation cannot proceed","HTML payload is empty or malformed — structured/skeleton modes may return sparse output","max_tokens set too low (below 20) — rejected by schema validation","mode=budget used without a query — BM25 ranking has no focus signal","Rate limiting or payment failure via x402 — 402 response with no content","Target page is behind authentication or a CAPTCHA — fetch returns empty or login HTML"],"whenToPreferThis":"Choose this endpoint when you need to reduce token overhead before feeding web content into an LLM — especially when working within strict context window budgets. It is preferable to raw fetch+truncation because it provides BM25-ranked relevance filtering, structured extraction modes, and quantified ROI metrics. Ideal for RAG pipelines, agent research tasks, and any workflow where web pages must be ingested cheaply and precisely.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:42.707Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-to-agent-ready-token-distiller-920545e1"}