Amazon Titan

Innovate responsibly with high-performing foundation models from Amazon

Benefits

Benefits

Meet Amazon Titan

Amazon Titan FMs are a family of FMs pretrained by AWS on large datasets, making them powerful, general purpose models built to support a variety of use cases. Use them as is or privately customize them with your own data.

Use Cases

  • Use Titan Text for creating copy for blog posts and web pages, classifying articles into categories, open-ended Q&A, and information extraction.

  • Get the gist of lengthy documents of text, such as reports and event books, with summaries based on natural language prompts.

  • Use Titan Embeddings for applications like personalization and search. By comparing embeddings, the model can produce more relevant and contextual responses than word matching.

  • Deliver more up-to-date and accurate results for user queries by connecting FMs to your data sources.

Use Cases

  • Use Titan Text for creating copy for blog posts and web pages, classifying articles into categories, open-ended Q&A, and information extraction.

  • Get the gist of lengthy documents of text, such as reports and event books, with summaries based on natural language prompts.

  • Use Titan Embeddings for applications like personalization and search. By comparing embeddings, the model can produce more relevant and contextual responses than word matching.

  • Deliver more up-to-date and accurate results for user queries by connecting FMs to your data sources.

Model versions

Titan Text Express (preview)

A large language model offering a balance of price and performance.

Max tokens: 8K

Languages: 100+ languages

Supported use cases: Retrieval augmented generation, open ended text generation, brainstorming, summarization, code generation, table creation, data formatting, paraphrasing, chain of thought, rewrite, extraction, Q&A, chat.

Titan Text Lite (preview)

Affordable and compact, ideal for basic tasks and fine-tuning.

Max tokens: 4K

Languages: English

Supported use cases: Open ended text generation, brainstorming, summarization, code generation, table creation, data formatting, paraphrasing, chain of thought, rewrite, extraction, Q&A, chat.

Titan Embeddings (generally available)

Large language model that translates text into a numerical representation.

Max tokens: 8K

Languages: 25+ languages

Embeddings: 1,536

Supported use cases: Text retrieval, semantic similarity, clustering.