Amazon Bedrock now supports Batch inference for Anthropic Claude Sonnet 4 and OpenAI GPT-OSS models
News
Amazon Bedrock now supports Batch inference for Anthropic Claude Sonnet 4 and OpenAI GPT-OSS models, offering improved performance and cost-effectiveness for large-scale AI workloads.
- Batch inference enables asynchronous processing of multiple inference requests
- 50% lower pricing compared to on-demand inference
- Supports use cases like document analysis, content generation, and data extraction
- Optimized for higher batch throughput on newer models
- Includes Amazon CloudWatch metrics to track batch workload progress
This update makes it easier and more cost-effective for organizations to process high-volume AI tasks using foundation models from leading providers.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Sep 3
2025
2025
Amazon Bedrock now supports Global Cross-Region inference for Anthropic Claude Sonnet 4
Aug 20
2025
2025
Amazon Bedrock now provides simplified access to OpenAI open weight models
Feb 27
2026
2026
Amazon Bedrock batch inference now supports the Converse API format
Nov 21
2024
2024
Using responsible AI principles with Amazon Bedrock Batch Inference
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.