{"uid":"cap_moleyjM7QFc_CuN72-KyD","slug":"one-engine-unicode-nfkc-normalization-t5-1f66d3c2","name":"ONE Engine Unicode NFKC Normalization (T5)","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-normalize/unicode-nfkc/t5?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":"0.0025","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":"$0.0025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_sZ3OXT6cry4_wqZrjQQ5D","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0025","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Normalizes input text to Unicode NFKC form using the T5 model, resolving compatibility characters and canonicalizing encoding.","exampleAgentPrompt":"Please normalize this text to NFKC unicode form — it has mixed compatibility characters and ligatures that need to be canonicalized before I run NLP on it: 'Ａｂｃ file ½ ①'","exampleUseCases":[{"title":"NLP pipeline text preprocessing","prompt":"Before I run this multilingual corpus through my language model, normalize all the text to NFKC unicode — there are a bunch of half-width katakana, ligatures, and compatibility symbols that need to be canonicalized."},{"title":"Cleaning scraped web content","prompt":"I scraped a bunch of product descriptions from various websites and they have weird unicode artifacts like ① ② fi and ½ — can you NFKC-normalize the text so it's consistent before I index it?"},{"title":"Standardizing user input before search","prompt":"A user just typed '６ｐｍ Ａｍｓｔｅｒｄａｍ' using full-width characters — normalize it to standard NFKC unicode so my search system can match it correctly."}],"resultDescription":"Returns a JSON object containing the NFKC-normalized version of the input text, with compatibility characters decomposed and canonically recomposed, ligatures expanded, and encoding standardized.","failureModes":["Text exceeds 50000 character limit — request rejected","Empty or missing 'text' field — validation error","Payment not included or insufficient USDC — 402 Payment Required response","Malformed JSON body — 400 Bad Request","Service unavailable on Cloudflare Workers — 503 or timeout"],"whenToPreferThis":"Choose this endpoint when you need lightweight, pay-per-call NFKC unicode normalization without managing your own NLP infrastructure — especially useful for agents preprocessing text before embedding, search, or model inference. Prefer it over general-purpose NLP APIs when you specifically need unicode canonicalization at low cost ($0.0025/call) and want to pay per use via x402 on Base rather than maintain a subscription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T12:44:14.690Z","isFirstParty":false,"canonicalSlug":"one-engine-unicode-nfkc-normalization-t5-1f66d3c2"}