中EN Submit a tool

PaLM 2

LLMs

Google’s next-generation large language model with 340B+ parameters, covering 100+ languages, with strengthened math, coding, and reasoning. It ships in four sizes from Gecko to Unicorn.

Human verified · · Submit a correction

Visit website
Editor's note

Suited to AI developers, researchers, and enterprise teams in the Google ecosystem; not for everyday users seeking a ready-made consumer chatbot.

Verified facts

CategoryLLMs
Human verified

What is PaLM 2

Google’s next-generation large language model with 340B+ parameters, covering 100+ languages, with strengthened math, coding, and reasoning. It ships in four sizes from Gecko to Unicorn.

Key features of PaLM 2

  • Building dialogue, summarization, and translation apps via API
  • Multilingual content generation for global products
  • Assisting Python/JavaScript development with code generation
  • Running offline on-device AI with the lightweight Gecko version

Good for

  • 340B+ parameters with 100+ language coverage
  • Notably improved math, reasoning, and coding over the first generation
  • Four sizes available; Gecko runs offline on mobile devices

Watch out

  • Developer-oriented, no direct consumer product entry
  • Capabilities bound to the Google ecosystem
  • Released in 2023 and since succeeded by newer models; partly historical material

How to use PaLM 2

  1. Visit the Google AI page to learn PaLM 2 capabilities
  2. Apply for developer access or API quota
  3. Choose a model size for your workload (Gecko for on-device)
  4. Call the API and design prompts for your task
  5. Integrate into your product and keep evaluating output quality

Who PaLM 2 is for

Difficulty: Advanced

  • Building dialogue, summarization, and translation apps via API
  • Multilingual content generation for global products
  • Assisting Python/JavaScript development with code generation
  • Running offline on-device AI with the lightweight Gecko version

FAQ

How is PaLM 2 different from a regular chatbot?

PaLM 2 is a foundation LLM that can be trained into a conversational system and also used for summarization, translation, and coding tasks.

How many versions does PaLM 2 have?

Four sizes, from smallest to largest: Gecko, Otter, Bison, and Unicorn; Gecko can run offline on mobile devices.

How is PaLM 2 priced?

The listing publishes no pricing; costs typically depend on API volume and model version, per Google’s developer docs and billing pages.

Sources and verification

Sources: ai.google (opens in a new tab)
Verified: · Submit a correction →

Alternatives to PaLM 2

All in this category
MMLU Best for: researchers and engineers measuring an English model's general knowledge; not for: assessing generation quality, dialogue experience, or Chinese ability. Watsonx.ai Best for mid-to-large enterprises and development teams needing full-lifecycle model management with enterprise governance and compliance; not for individual developers, lightweight experiments or budget-sensitive small projects. DeepFloyd IF Best for developers and researchers who want to self-host and study an image generation model in depth; not suitable for casual users who just want to type a prompt on a webpage and get an image. HELM Suited to researchers and engineering teams needing multi-dimensional, reproducible LLM evaluation; not for users who only want a quick single-score leaderboard. PubMedQA Ideal for biomedical NLP researchers training and benchmarking literature QA models; not for end users seeking a ready-made medical Q&A product.