{"uid":"cap_KHz96ibeX1Yenjj0evLX_","slug":"agentdiet-a2a-context-window-distiller-9b808337","name":"AgentDiet A2A Context Window Distiller","description":"Deterministic HTML/DOM/JSON/RAG context distiller that strips 85-97% of token bloat before LLM ingestion while preserving 100% of semantic entities, citations, and code blocks.","url":"https://agentdiet.dev/v1/dex?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"token":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_-GUi1VA47v2EMzNl78cWd","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Strips 85-97% of token bloat from HTML, DOM, JSON, or RAG content before LLM ingestion while preserving all semantic entities, citations, and code blocks.","exampleAgentPrompt":"Take this web page and distill it down to agent-ready tokens — strip all the HTML bloat and noise but keep every meaningful fact, citation, and code block so I can feed it cleanly into my LLM without burning my context window.","exampleUseCases":[{"title":"RAG pipeline token cost reduction","prompt":"I'm building a RAG pipeline and my chunks are way too large — can you run this HTML document through AgentDiet and strip out all the boilerplate so I only pass the semantic content to the LLM?"},{"title":"Compress scraped page for agent reasoning","prompt":"I just scraped this product documentation page and it's 40,000 tokens of messy HTML. Distill it down to just the meaningful content so my agent can reason over it without blowing the context window."},{"title":"Trim JSON context before LLM call","prompt":"I have a huge JSON payload from a RAG retrieval step — can you compress it to remove redundant structure and token bloat while keeping all the data my LLM actually needs to answer the question?"}],"resultDescription":"Returns a distilled, semantically-intact version of the input content with all token bloat removed. The response includes a `data` object containing the compressed output and a `roi_proof` field showing the compression ratio percentage (e.g. 91.4%), plus a status field confirming success.","failureModes":["Invalid or unreachable URL returns an error with no distilled output","Malformed input type or missing required fields returns a schema validation error","Content that is already minimal may return low compression ratios","Rate limiting or payment failure via x402 protocol blocks the request","Extremely large payloads may time out before distillation completes"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before LLM calls and cannot afford to lose semantic fidelity — especially for HTML-heavy web pages, verbose JSON payloads, or large RAG context chunks. It is deterministic (not generative), so compression is consistent and auditable. Prefer it over manual chunking or summarization when you need guaranteed preservation of citations, entities, and code blocks alongside maximum compression.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:39:05.133Z","isFirstParty":false,"canonicalSlug":"agentdiet-a2a-context-window-distiller-9b808337"}