Google Gemma 4 models available on Amazon Bedrock
AWS has announced the integration of Google DeepMind's Gemma 4 family of open-weight models into Amazon Bedrock. These models enable the development of generative AI applications for reasoning, multimodal understanding, agentic workflows, and software engineering. The Gemma 4 family includes three variants optimized for different use cases, all running on a new, price-performant Bedrock innovation. The models are now available in select AWS regions.
- →Gemma 4 models integrated into Amazon Bedrock
- →Three Gemma 4 variants support diverse use cases
- →Optimized performance and features for Gemma 4 on Bedrock
- →Gemma 4 models support multimodal input and 35+ languages
- →Availability in select AWS Regions
Features (2) ›
- Gemma 4 models integrated into Amazon Bedrock
The Gemma 4 family of open-weight models from Google DeepMind is now available on Amazon Bedrock, offering enhanced capabilities for generative AI applications.
- Three Gemma 4 variants support diverse use cases
The family includes Gemma 4 31B for reasoning and coding, Gemma 4 26B-A4B for cost and latency sensitive workloads, and Gemma 4 E2B for low-latency interactive applications.
Enhancements (1) ›
- Optimized performance and features for Gemma 4 on Bedrock
Gemma 4 models run on a new Bedrock innovation designed for price performance, with improved support for tool calling, structured output, reasoning, and response streaming.
Notes (2) ›
- Gemma 4 models support multimodal input and 35+ languages
The models feature built-in reasoning, native function calling, and support for multimodal inputs including text, image, video, and audio, along with over 35 languages.
- Availability in select AWS Regions
Gemma 4 models are available in AWS US East (N. Virginia), US East (Ohio), US West (Oregon), and Europe (Frankfurt) regions.
https://aws.amazon.com/about-aws/whats-new/2026/06/gemma-4-amazon-bedrock/