{"uid":"cap_jUZagEh6aGCnfeka3Ig3j","slug":"company-enrich-agentdiet-dev-rag-token-diet-web-url-distiller-dc8b1fd8","name":"RAG Token Diet — Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://company-enrich.agentdiet.dev/v1/rag-token-diet)","url":"https://company-enrich.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_Fok9_CTkCZQBEI5BtsH70","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage (or accepts raw HTML) and compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/payment-intents into compact markdown using budget mode, focused on 'payment lifecycle', and cap it at 500 tokens.","exampleUseCases":[{"title":"RAG pipeline token budget enforcement","prompt":"I need to feed this documentation page https://docs.openai.com/api-reference into my RAG pipeline — can you distill it into budget mode focused on 'embeddings API' and keep it under 300 tokens?"},{"title":"Structured data extraction from product page","prompt":"Pull https://www.crunchbase.com/organization/stripe and give me the structured mode output — I want tables and metadata, not raw HTML or prose."},{"title":"Skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and return just the skeleton outline so I can see the document structure without burning my whole context window."}],"resultDescription":"Returns a JSON object containing the distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus ROI proof metrics (raw token count, distilled token count, tokens saved, compression ratio %, LLM cost saved in USD), billing details, and cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may produce unfiltered output","Very large pages may hit processing limits or return partial distillations","Paywalled or JavaScript-heavy pages may yield low-quality or empty distillations","Missing required 'url' parameter returns a validation error","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window but want to minimize token usage and cost — especially when working with long documentation pages, large HTML payloads, or RAG pipelines with strict token budgets. The BM25 budget mode makes it uniquely suited for query-focused extraction where only the most relevant passages matter. Prefer it over raw web scraping when the downstream consumer is an LLM that charges per token.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:19.333Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-rag-token-diet-web-url-distiller-dc8b1fd8"}