---
title: "Introducing Gemma 4 models on Amazon Bedrock"
slug: "introducing-gemma-4-models-on-amazon-bedrock"
date: 2026-06-15
category: tech-pub
tags: [google, reasoning, amazon]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/introducing-gemma-4-models-on-amazon-bedrock
---

# Introducing Gemma 4 models on Amazon Bedrock

**Published**: 2026-06-15 | **Category**: tech-pub | **Sources**: 1

---

## TL;DR

- AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.

---

## Summary

- AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.
- The lineup includes Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B. 31B is dense, 26B-A4B uses Mixture-of-Experts with 3.8B active parameters, and E2B targets low-latency use cases.
- All variants support text and image input, reasoning, native function calling, system prompts, plus Bedrock’s Standard, Priority, and Flex service tiers.
- AWS highlights an OpenAI-compatible API for Chat Completions and Responses. In practice, migration may be as small as changing the base URL and model ID, while IAM and pricing stay AWS-specific.

---

## Why it matters

AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.

---

## Key Points

- AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.
- The lineup includes Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B. 31B is dense, 26B-A4B uses Mixture-of-Experts with 3.8B active parameters, and E2B targets low-latency use cases.
- All variants support text and image input, reasoning, native function calling, system prompts, plus Bedrock’s Standard, Priority, and Flex service tiers.
- AWS highlights an OpenAI-compatible API for Chat Completions and Responses. In practice, migration may be as small as changing the base URL and model ID, while IAM and pricing stay AWS-specific.

---

## Nauti's Take

AWS frames this heavily as an infrastructure story, and that is where the value actually sits. Gemma 4 becomes more useful for many teams once it fits into existing stacks with IAM, short-lived keys, S3 images, tool calling, and familiar SDKs. The PR-heavy part is the benchmark shine: an Intelligence Index helps with orientation, but it is not a substitute for your own tests. Bedrock users should try E2B for cheap multimodal classification and 26B-A4B for throughput before making 31B the default.

---


## FAQ

**Q:** What is Introducing Gemma 4 models on Amazon Bedrock about?

**A:** - AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.

**Q:** Why does it matter?

**A:** AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.

**Q:** What are the key takeaways?

**A:** AWS made Gemma 4 available on Amazon Bedrock on June 15, 2026: three instruction-tuned open-weight models from Google DeepMind under Apache 2.0, served through the new bedrock-mantle endpoint.. The lineup includes Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B. 31B is dense, 26B-A4B uses Mixture-of-Experts with 3.8B active parameters, and E2B targets low-latency use cases.. All variants support text and image input, reasoning, native function calling, system prompts, plus Bedrock’s Standard, Priority, and Flex service tiers.

---

## Related Topics

- [google](https://news.ainauten.com/en/tag/google)
- [reasoning](https://news.ainauten.com/en/tag/reasoning)
- [amazon](https://news.ainauten.com/en/tag/amazon)

---

## Sources

- [Introducing Gemma 4 models on Amazon Bedrock](https://aws.amazon.com/blogs/machine-learning/introducing-gemma-4-models-on-amazon-bedrock/) - AWS Machine Learning Blog

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-06-16*