deGerman
Available95,5% strict-span F1
Documentation
Languages and data categories
See what ShinrAI 1.5 recognises, how coverage is measured and which API surface to use.
15 model locales
One multilingual model, with regional Portuguese variants and Hebrew in beta. Website languages and API language codes are separate.
No matching languages or categories.
enEnglish
Available97,3% strict-span F1
jaJapanese
Available98,5% strict-span F1
frFrench
Available96,4% strict-span F1
esSpanish
Available97,6% strict-span F1
itItalian
Available96,1% strict-span F1
plPolish
Available93,5% strict-span F1
pt-PTPortuguese · Portugal
Available94,6% strict-span F1
pt-BRPortuguese · Brazil
Available98,2% strict-span F1
ruRussian
Available96,9% strict-span F1
ukUkrainian
Available95,0% strict-span F1
trTurkish
Available93,2% strict-span F1
arArabic
Available90,1% strict-span F1
koKorean
Available95,2% strict-span F1
heHebrew
Beta71,2% strict-span F1
Business, medical and administrative documents; 200 texts per locale. Strict entity spans. Hebrew beta is included. Model-only evaluation by Innovius, not a service-wide accuracy guarantee.
View methodology and results →Model locales, API codes and website languages
The website is available in English, German, Japanese, French and Spanish. This does not limit the model to those five languages.
The documented Azure text adapter accepts these language codes:
de en fr es it pl pt ru uk tr ar he ja ko
Portuguese uses one API language code but has two evaluated regional model locales. An accepted code does not guarantee every entity category or equal quality.
Read the adapter limits →21 data categories
Examples are illustrative. Detection depends on the surrounding text and configuration.
People and organisations
People
Emma WeberPERSONOrganisations
Example GmbHCOMPANYContact and location
Cities
BerlinCITYStreet addresses
Musterstraße 12STREET_ADDRESSEmail addresses
emma@example.comEMAILPhone numbers
+49 30 000000PHONEPostal codes
10115POSTAL_CODEFinance
Bank accounts
DE89 3704 0044 0532 0130 00BANK_ACCOUNTCrypto wallets
0x…CRYPTO_WALLETPayment cards
4242 4242 4242 4242CREDIT_CARDPersonal identifiers
Dates of birth
14.03.1985DATE_OF_BIRTHNational identifiers
Tax / identity / social-security IDNATIONAL_IDVehicle plates
B AB 1234LICENSE_PLATECustomer and case IDs
CUSTOMER-0042CUSTOMER_IDDates and ages
Dates
12 March 2026DATEAges
42 yearsAGEDigital and confidential information
Usernames
example\emmaUSERNAMEWeb addresses
https://example.comURLNetwork addresses
192.0.2.1IP_ADDRESSSecrets and access tokens
API_KEY_EXAMPLESECRETProject codenames
Project AuroraPROJECT_CODENAMEWhy 21 categories and 29 classes?
The model has 21 detection heads. People, cities, streets and organisations each have three subtypes; the other 17 categories have one. That gives 29 classes, not 29 unrelated data categories.
PERSONcommon, uncommon, rareCITYmajor, medium, smallSTREET_ADDRESSgeneric, specific, localCOMPANYinternational, national, regional
Origin, name form and other attributes help choose appropriate replacements. They are additional attributes, not additional languages or guaranteed detections.
Enterprise detectors and API-specific coverage
Enterprise adds deterministic rules and validation for supported identifiers. These are not included in the model-only scores above.
Adapter examples include US social-security numbers, bank routing numbers, SWIFT codes and vehicle identification numbers. Coverage and required context vary by API.
Compatibility adapters expose their documented categories and operations. Unsupported options are rejected; unmapped findings can produce warnings. Use the native API when you need findings outside an adapter mapping.
Native API and compatibility documentation →