AWS – Jamba 1.5 family of models by AI21 Labs is now available in Amazon Bedrock

The Jamba 1.5 Model Family from AI21 Labs is now available in Amazon Bedrock. Jamba 1.5 Large and 1.5 Mini are cutting-edge foundation models designed for enterprise applications. With a 256k effective context window, one of the longest on the market, these models enable customers to tackle complex tasks like lengthy document summarization and analysis.

The Jamba 1.5 models, purpose-built for speed and efficiency with a hybrid architecture that makes them 2.5x faster than many other models (according to AI21), offer customers improved speed on long contexts, making them among the fastest in their size class. Jamba 1.5 Mini demonstrates exceptional performance, achieving a score of 46.1 on the Arena Hard benchmark, making it a leading public model in its category. With native support for structured JSON output, function calling, and document processing, the Jamba 1.5 models integrate into a wide range of enterprise business workflows, providing tailored solutions for your specialized, high-performance AI needs.

Jamba 1.5 Large – excels at complex reasoning tasks across all prompt lengths, making it ideal for applications that require high quality outputs on both long and short inputs.
Jamba 1.5 Mini – optimized for low-latency processing of long prompts, enabling fast analysis of lengthy documents and data.

AI21’s Jamba 1.5 models are available in Amazon Bedrock in the US East (N. Virginia) region. To learn more read the News Blog, visit the AI21 Labs in Amazon Bedrock page, and documentation. To get started with Jamba 1.5 in Amazon Bedrock, visit the Amazon Bedrock console.

Read More for the details.