No longer supported

This model is legacy (released May 2023) and is no longer actively maintained or recommended by Google. Consider using their current flagship model instead.

legacylegacyllm Proprietary

PaLM 2 Bison

by Google· Released May 2023· Cutoff Early 2023

PaLM 2 Bison is a large language model from Google, optimized for a wide range of natural language tasks such as text generation, classification, and chat. It is part of the PaLM 2 family, offering a balance of performance and efficiency, and has been succeeded by the Gemini models.

Official Site API Docs

Input cost

$0.50 per 1M tokens

Output cost

$1.50 per 1M tokens

Context window

8192 tokens

Max output

2048 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationChatCode GenerationClassificationSentiment AnalysisEntity ExtractionSummarization

Best For

General-purpose text generation and understanding tasks where cost efficiency is important.

Strengths

Strong multilingual capabilities
Efficient performance for a wide range of tasks
Good at code generation and understanding

Limitations

Smaller context window compared to newer models
No vision or multimodal support
Legacy status with limited future updates

Use Cases

Content creation and copywriting

Code generation and debugging

Customer support chatbots

Text classification and sentiment analysis

Language translation

Summarization of documents

Question answering

Improvements Over Previous Model

Introduced as a successor to PaLM, with improved multilingual and reasoning capabilities
Better efficiency and lower latency compared to PaLM
Enhanced code generation performance
Improved safety and responsible AI features

Back to all models