{"uid":"cap_Ah6P8mc1yFP4n5aNrP831","slug":"one-engine-word-bigrams-text-tokenizer-f20521fa","name":"ONE Engine Word Bigrams Text Tokenizer","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/word-bigrams/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_mXU2_FsZDeyfZ6eIDhXvc","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":"Extracts word-level bigrams (consecutive two-word pairs) from input text up to 50,000 characters","exampleAgentPrompt":"Can you extract all the word bigrams from this article text: 'The quick brown fox jumps over the lazy dog. The dog barked loudly at the fox.'?","exampleUseCases":[{"title":"NLP feature extraction for classifier","prompt":"I need to turn this product review into word bigram features for my sentiment classifier — here's the review: 'The battery life is amazing but the screen resolution is disappointing compared to competitors.'"},{"title":"Keyword pair analysis for SEO","prompt":"Extract all consecutive word pairs from this blog post so I can see which two-word phrases appear most often and optimize for them: 'Content marketing drives traffic. Good content marketing builds authority and drives organic traffic.'"},{"title":"Text similarity preprocessing pipeline","prompt":"Take this paragraph and break it into word bigrams so I can use them as features for a document similarity comparison: 'Machine learning models require large datasets for training and produce accurate predictions when properly tuned.'"}],"resultDescription":"Returns a JSON object containing word bigrams extracted from the input text — consecutive two-word token pairs derived by sliding a window of size 2 across the tokenized words in the text.","failureModes":["Text exceeds 50,000 character limit — request rejected or truncated","Empty or whitespace-only text input returns empty bigram set","Payment failure via x402 protocol on Base blocks the call","Malformed JSON request body returns error response","Text with only one word produces no bigrams"],"whenToPreferThis":"Choose this endpoint when you need word-level bigram tokenization specifically — not character n-grams or skip-grams — and want a cheap, pay-per-call option without a subscription. Ideal for NLP preprocessing pipelines, feature engineering for text classifiers, or co-occurrence analysis tasks where you need consecutive two-word pairs from text up to 50K characters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T12:44:00.910Z","isFirstParty":false,"canonicalSlug":"one-engine-word-bigrams-text-tokenizer-f20521fa"}