PaLM 2
PaLM 2 is a text generation model from Google built on the Pathways AI architecture with an 8,000-token context window.
Google's language model for complex text tasks
PaLM 2, short for Pathways Language Model 2, is a large language model developed by Google and built on Google's Pathways AI architecture. It is designed for text generation tasks including natural language understanding, conversation, and creative content generation. The model supports a context window of 8,000 tokens and a maximum response size of 1,024 tokens.
PaLM 2 was made available through Google's AI products and APIs, including Google Cloud's Vertex AI platform. It is suited for applications requiring contextual language understanding, multi-turn conversation, and structured text generation. The model has since been marked as deprecated, meaning Google no longer actively develops or recommends it for new projects.
What PaLM 2 supports
Text Generation
Generates natural language text across a range of formats and styles. Supports a maximum response size of 1,024 tokens per output.
Contextual Understanding
Processes and reasons over input within an 8,000-token context window, enabling multi-turn conversations and longer document handling.
Creative Content
Supports generation of creative text such as stories, summaries, and structured prose based on user prompts.
Multilingual Support
PaLM 2 was trained on a multilingual corpus, giving it the ability to understand and generate text in multiple languages.
Code Generation
Capable of generating and explaining code across common programming languages, a capability highlighted in Google's PaLM 2 technical report.
Reasoning Tasks
Handles multi-step reasoning tasks including logical inference and structured problem-solving based on natural language input.
Ready to build with PaLM 2?
Get Started FreeCommon questions about PaLM 2
What is the context window size for PaLM 2?
PaLM 2 supports a context window of 8,000 tokens, which includes both the input prompt and the generated response.
What is the maximum response length PaLM 2 can produce?
The maximum response size for PaLM 2 is 1,024 tokens per generation.
Is PaLM 2 still available for use?
PaLM 2 is currently marked as deprecated. Google has moved toward newer model families, so it is not recommended for new projects.
Who developed PaLM 2?
PaLM 2 was developed by Google and is built on Google's Pathways AI architecture.
What types of tasks is PaLM 2 designed for?
PaLM 2 is designed for text generation tasks including natural language understanding, multi-turn conversation, creative writing, code generation, and reasoning.
Parameters & options
Explore similar models
GoogleGemini 3.7 Flash
Gemini 3.7 Flash is a text generation model from Google with a 1,048,576-token context window and configurable thinking levels.
GoogleGemini 3.5 Flash Lite
Gemini 3.5 Flash Lite is a text generation model from Google designed for low-cost, real-time tasks with a 1M token context window.
GoogleGemini 3.6 Flash
Gemini 3.6 Flash is a text and image understanding model from Google with a 1,048,576-token context window.
OpenAIGPT 5.6 Luna
GPT 5.6 Luna is a text and image-input model from OpenAI with a 1,050,000-token context window.
DeepSeekDeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a text generation model from DeepSeek with a 1,048,576-token context window and configurable reasoning effort.
X.aiGrok 4.6
Grok 4.6 is a text generation model from X.ai featuring a 500,000-token context window and configurable reasoning effort.
Start building with PaLM 2
No API keys required. Create AI-powered workflows with PaLM 2 in minutes — free.