Box Developer Documentation

Google Text Bison 32k

Google Text Bison 32k

Google Text Bison 32k is a multimodal model designed to handle lightweight tasks. This model supports a long context window, making it highly suitable for tasks involving large text input, such as summarization or code analysis.

Model details

ItemValueDescription
Model nameGoogle Text Bison 32kThe name of the model.
API model namegoogle__text_bison_32kThe name of the model that is used in the Box AI API for model overrides. The user must provide this exact name for the API to work.
Hosting layerGoogleThe trusted organization that securely hosts LLM.
Model providerGoogleThe organization that provides this model.
Release dateSeptember 2023The release date for the model.
Knowledge cutoff date2023The date after which the model does not get any information updates.
Input context window32k tokensThe number of tokens supported by the input context window.
Maximum output tokens8k tokensThe number of tokens that can be generated by the model in a single request.
Empirical throughputNot specifiedThe number of tokens the model can generate per second.
Open sourceNoSpecifies if the model's code is available for public use.

Additional documentation

For additional information, see official Google Text Bison documentation.