Pretrained Models

Learn about the Language service pretrained models.

Single Requests

  • A record can be up to 1,000 characters. We encourage you to use Batch Requests that support records up to 5,000 characters and support more than one record in a single request.

  • There's no minimum number of characters that must be provided, but the output quality is highly dependent on the amount of information provided to the models.

Batch Requests

  • A batch can have up to 100 records.

  • A record can be up to 5,000 characters long.

  • The total number of characters to process in a request can be up to 20,000 characters.

Multilingual

OCI Language pre-trained models support multilingual text. These pre-trained models provide state of the art accuracy levels for analyzing unstructured text.

Pretrained Multilingual (v2) models are available through dedicated endpoint.

Model Model v1 Languages Supported Model v2 Languages Supported
Sentiment Analysis

English, Spanish

English, Spanish, Arabic, German, French, Italian

And 100+ languages by design

Pre-trained Named Entity Recognition

English, Spanish

English, Spanish, Arabic, German, French, Italian

And 100+ languages by design

Key Phrase Extraction

English, Spanish

English, Spanish, Arabic, German, French, Italian

And 100+ languages by design

Language Detection 100+ languages
Custom text Classification 15 languages supported by design
Custom Named Entity Recognition 7 languages supported by design
PII identification and de-identification English
Pre-trained Text Classification English