{"uid":"cap_jOP0-EWpgl_1j0mrOWgLp","slug":"one-engine-text-tokenization-sentence-splitter-t4-dc278edf","name":"ONE Engine Text Tokenization – Sentence Splitter (T4)","description":"Low-cost pay-per-call utility APIs for autonomous agents using x402 on Base.","url":"https://one-search.one-engine.workers.dev/v3/text-token/sentences/t4?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["text"],"properties":{"text":{"type":"string","description":"Text up to 50000 characters"}}},"responseSchema":{"type":"object","additionalProperties":true},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0015","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":"$0.0015/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_TTYtIPegH9luyysTEP4OY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0015","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Splits input text into individual sentences using token-level analysis, returning a list of sentence tokens extracted from the provided text.","exampleAgentPrompt":"Can you split this paragraph into individual sentences: 'The quick brown fox jumped over the lazy dog. It was a bright sunny day. Nobody expected what happened next.'","exampleUseCases":[{"title":"Preprocessing article for NLP pipeline","prompt":"I have this 2000-word news article and I need it broken into individual sentences so I can run sentiment analysis on each one — can you split it up for me?"},{"title":"Counting sentences in legal document","prompt":"Take this contract clause and split it into its individual sentences so I can see exactly how many statements it contains: 'The licensee agrees to all terms herein. Violations will result in termination. All disputes shall be settled by arbitration.'"},{"title":"Chunking text for summarization agent","prompt":"Break this long research abstract into separate sentences so I can process each one individually: 'Machine learning has transformed data science. Models now outperform humans on many benchmarks. However, interpretability remains a major challenge. Researchers are actively developing explainability tools.'"}],"resultDescription":"Returns a structured JSON object containing the input text segmented into an array of individual sentences, enabling downstream per-sentence processing, analysis, or display.","failureModes":["Text exceeds 50000 character limit — request rejected or truncated","Empty text input returns empty sentence array or error","Ambiguous sentence boundaries (abbreviations, ellipses) may cause mis-splits","Payment failure via x402 if USDC balance is insufficient","Malformed JSON request body returns 4xx error"],"whenToPreferThis":"Choose this endpoint when you need lightweight, low-cost sentence-level tokenization of text up to 50000 characters within an autonomous agent workflow that already supports x402 micropayments on Base. Ideal for preprocessing steps in NLP pipelines where per-call cost efficiency matters and no heavy NLP library is available in the agent runtime.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T12:44:25.911Z","isFirstParty":false,"canonicalSlug":"one-engine-text-tokenization-sentence-splitter-t4-dc278edf"}