{"uid":"cap_IjVKxz8vWFKSREtMvOW_G","slug":"402utils-extractive-text-summarizer-25ae9d3f","name":"402utils Extractive Text Summarizer","description":"Extractive summary: selects the N most salient sentences via TextRank (TF-IDF cosine + PageRank) — a pure algorithm, no LLM, so deterministic and free of inference cost. Returns the summary and each chosen sentence with a salience score and index. Extractive (selects existing sentences), NOT abstractive/generative — that is the point: reproducible and model-free. Pre-condense a page before an LLM call. Provided text only. Over 1 MB truncated.","url":"https://402utils.com/v1/summarize-extractive","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","description":"The text to summarize (max 1 MB UTF-8; larger is truncated)."},"sentences":{"type":"integer","default":3,"maximum":50,"minimum":1,"description":"How many sentences to select."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_B2JZnmngjIbe_l_wdPjOF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Selects the N most salient sentences from input text using TextRank (TF-IDF cosine + PageRank), returning each chosen sentence with a salience score and index — deterministic, model-free, no LLM.","exampleAgentPrompt":"Can you give me an extractive summary of this article — pick the 5 most important sentences using the deterministic TextRank algorithm, not an LLM: [paste article text here]","exampleUseCases":[{"title":"Pre-condense research papers for analysis","prompt":"I'm reviewing 20 research papers tonight. Can you pull out the 7 most salient sentences from each one using TextRank so I can skim them faster before I send them to my AI analyst? I need the exact original sentences, not a rewrite."},{"title":"Reduce support ticket volume before routing","prompt":"We're getting swamped with long customer emails. Can you extract the 4 most important sentences from each incoming ticket using the deterministic TextRank method? That way my team can spot the real issue without reading walls of text."},{"title":"Cut LLM token costs on long documents","prompt":"I have a 15-page legal document I need analyzed, but I'm worried about token costs. Can you give me the 10 key sentences using TextRank first? Then I'll send just those to my LLM instead of the whole thing."}],"resultDescription":"Returns a summary string composed of the N selected sentences, plus an array of objects each containing the chosen sentence text, its salience score (float), and its original index in the source text.","failureModes":["Text over 1 MB is silently truncated before processing","Invalid 'sentences' value outside 1–50 range may return an error or be clamped","Empty or very short text may yield fewer sentences than requested","Payment failure (402) if USDC funds are insufficient","Non-UTF-8 encoded text may cause parsing errors"],"whenToPreferThis":"Use this endpoint when you need a deterministic, reproducible extractive summary with no LLM inference cost — ideal for pre-condensing large documents before passing to an LLM to reduce token usage, or when you need the same input to always yield the same output without model variance. Prefer over abstractive/generative summarizers when fidelity to original wording matters and hallucination risk must be zero.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:57:07.257Z","isFirstParty":false}